Source author record

Chen Chen

Chen Chen appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Catalog footprint

What is connected

168works

47topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinations and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex question reasoning. We formalize multi-agent collaboration with external tools as a trajectory preference alignment problem, incorporating question-aware agent customization and inter-agent preference harmonization. AMATA introduces two principal innovations: (1) Intra-Trajectory Preference Learning, which learns objective-oriented preferences to prioritize critical agents, and (2) Inter-Agent Dependency Learning, which captures cross-agent tool dependencies through a novel dependency-aware direct preference optimization technique. Empirical results show that AMATA consistently outperforms baseline approaches, knowledge-augmented frameworks, and LLM-based trajectory systems on five established knowledge-intensive QA benchmarks. Further analysis demonstrates the efficiency of our method in reducing token consumption.

preprint2026arXiv

Anchor-guided Hypergraph Condensation with Dual-level Discrimination

The increasing prevalence of large-scale hypergraphs poses significant computational challenges for hypergraph neural network (HNN) training. To address this, hypergraph condensation (HGC) distills large real hypergraphs into compact yet informative synthetic ones, beyond graph condensation (GC) methods limited to pairwise relations. However, existing HGC methods rely on decoupled training architectures, where structure generators are pre-trained on the original hypergraph but not jointly optimized with condensed features during refinement, resulting in misaligned structures that degrade downstream utility. Moreover, trajectory-based optimization incurs substantial computational overhead in refinement, limiting condensation efficiency. To tackle these issues, we propose \textbf{A}nchor-guided \textbf{H}yper\textbf{G}raph \textbf{C}ondensation with \textbf{D}ual-level \textbf{D}iscrimination (\textbf{AHGCDD}), which consists of three key components: (1) a node initialization module based on Heat Kernel PageRank (HKPR) to encode structural knowledge into feature semantics; (2) an anchor-guided hyperedge synthesis strategy for joint optimization of condensed features and structure; (3) a theoretically grounded dual-level discrimination objective for utility-preserving condensation without redundant HNN training. Extensive experiments demonstrate the superior effectiveness and efficiency of AHGCDD.

preprint2026arXiv

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model's original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, where perception errors and reasoning failures follow distinct drift patterns that compound during subsequent RL. We introduce PRISM, a three-stage pipeline that mitigates this drift by inserting an explicit distribution-alignment stage between SFT and RLVR. Building on the principle of on-policy distillation (OPD), PRISM casts alignment as a black-box, response-level adversarial game between the policy and a Mixture-of-Experts (MoE) discriminator with dedicated perception and reasoning experts, providing disentangled corrective signals that steer the policy toward the supervision distribution without requiring access to teacher logits. While 1.26M public demonstrations suffice for broad SFT initialization, distribution alignment demands higher-fidelity supervision; we therefore curate 113K additional demonstrations from Gemini 3 Flash, featuring dense visual grounding and step-by-step reasoning on the hardest unsolved problems. Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0 points over the SFT-to-RLVR baseline on 4B and 8B, respectively. Our code, data, and model checkpoints are publicly available at https://github.com/XIAO4579/PRISM.

preprint2026arXiv

Communication-Efficient Federated AUC Maximization with Cyclic Client Participation

Federated AUC maximization is a powerful approach for learning from imbalanced data in federated learning (FL). However, existing methods typically assume full client availability, which is rarely practical. In real-world FL systems, clients often participate in a cyclic manner: joining training according to a fixed, repeating schedule. This setting poses unique optimization challenges for the non-decomposable AUC objective. This paper addresses these challenges by developing and analyzing communication-efficient algorithms for federated AUC maximization under cyclic client participation. We investigate two key settings: First, we study AUC maximization with a squared surrogate loss, which reformulates the problem as a nonconvex-strongly-concave minimax optimization. By leveraging the Polyak-Łojasiewicz (PL) condition, we establish a state-of-the-art communication complexity of $\widetilde{O}(1/ε^{1/2})$ and iteration complexity of $\widetilde{O}(1/ε)$. Second, we consider general pairwise AUC losses. We establish a communication complexity of $O(1/ε^3)$ and an iteration complexity of $O(1/ε^4)$. Further, under the PL condition, these bounds improve to communication complexity of $\widetilde{O}(1/ε^{1/2})$ and iteration complexity of $\widetilde{O}(1/ε)$. Extensive experiments on benchmark tasks in image classification, medical imaging, and fraud detection demonstrate the superior efficiency and effectiveness of our proposed methods.

preprint2026arXiv

Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration

The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialised domains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) pre-trained on natural images, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific fine-tuning. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D and 3D classification, segmentation, and registration on a wide range of medical imaging modalities. We systematically analyse its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialisation, such as in whole-slide images (WSIs), electron microscopy (EM), and positron emission tomography (PET). Furthermore, we observe that DINOv3 does not consistently follow the scaling law in the medical domain. Its performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviours across tasks. Overall, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.

preprint2026arXiv

FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery

Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity is not uniform across the body, as torso pose and root structure are often relatively well constrained, whereas distal articulations such as the arms and legs are more uncertain. Building on this observation, we propose FactorizedHMR, a two-stage framework that treats these two regimes differently. A deterministic regression module first recovers a stable torso-root anchor, and a probabilistic flow-matching module then completes the remaining non-torso articulation. To make this completion reliable, we combine a composite target representation with geometry-aware supervision and feature-aware classifier-free guidance, preserving the torso-root anchor while improving single-reference recovery of ambiguity-prone articulation. We also introduce a synthetic data pipeline that provides the paired image-camera-motion supervision under diverse viewpoints. Across camera-space and world-space benchmarks, FactorizedHMR remains competitive with strong baselines, with the clearest gains in occlusion-heavy recovery and drift-sensitive world-space metrics.

preprint2026arXiv

GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents

Recent advances in vision-language models (VLMs) and reinforcement learning (RL) have driven progress in GUI automation. However, most existing methods rely on static, one-shot visual inputs and passive perception, lacking the ability to adaptively determine when, whether, and how to observe the interface. We present GUI-Eyes, a reinforcement learning framework for active visual perception in GUI tasks. To acquire more informative observations, the agent learns to make strategic decisions on both whether and how to invoke visual tools, such as cropping or zooming, within a two-stage reasoning process. To support this behavior, we introduce a progressive perception strategy that decomposes decision-making into coarse exploration and fine-grained grounding, coordinated by a two-level policy. In addition, we design a spatially continuous reward function tailored to tool usage, which integrates both location proximity and region overlap to provide dense supervision and alleviate the reward sparsity common in GUI environments. On the ScreenSpot-Pro benchmark, GUI-Eyes-3B achieves 44.8% grounding accuracy using only 3k labeled samples, significantly outperforming both supervised and RL-based baselines. These results highlight that tool-aware active perception, enabled by staged policy reasoning and fine-grained reward feedback, is critical for building robust and data-efficient GUI agents.

preprint2026arXiv

Large Language Models are Universal Reasoners for Visual Generation

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural unification, these systems frequently fail to faithfully align complex prompts during synthesis, even though they remain highly accurate at verifying whether an image satisfies those same prompts. We formalize this as the \emph{understanding-generation gap} and propose UniReasoner, a framework that leverages the LLM as a universal reasoner to convert its understanding strength into direct generation guidance. Given a prompt, the LLM first produces a coarse visual draft composed of discrete vision tokens. It then performs a self-critique by evaluating the draft for prompt consistency, producing a grounded textual evaluation that pinpoints what needs to be corrected. Finally, a diffusion model is conditioned jointly on the prompt, the visual draft, and the evaluation, ensuring that generation is guided by explicit corrective signals. Each signal addresses a limitation of the other: the draft provides a concrete, scene-level anchor that reduces under-specification in text-only conditioning, while the evaluation turns verification into grounded, actionable constraints that correct omissions, hallucinations, and relational errors. Experiments show that UniReasoner improves compositional alignment and semantic faithfulness under the same diffusion backbone while maintaining image quality, demonstrating a practical way to exploit LLM reasoning to close the understanding-generation gap.

preprint2026arXiv

Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization

Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally critical in prompt engineering, where designing effective prompts for large language models constitutes a complex optimization challenge. A structured optimization approach requires automated or semi-automated procedures to develop improved prompts, thereby reducing manual effort, improving performance, and yielding an interpretable process. However, current prompt optimization methods often induce prompt drift, where new prompts fix prior failures but impair performance on previously successful tasks. Additionally, generating prompts from scratch can compromise interpretability. To address these limitations, this study proposes the Hierarchical Attribution Prompt Optimization (HAPO) framework, which introduces three innovations: (1) a dynamic attribution mechanism targeting error patterns in training data and prompting history, (2) semantic-unit optimization for editing functional prompt segments, and (3) multimodal-friendly progression supporting both end-to-end LLM and LLM-MLLM workflows. Applied in contexts like single/multi-image QA (e.g., OCRV2) and complex task analysis (e.g., BBH), HAPO demonstrates enhanced optimization efficiency, outperforming comparable automated prompt optimization methods and establishing an extensible paradigm for scalable prompt engineering.

preprint2026arXiv

Lifelong Domain Adaptive 3D Human Pose Estimation

3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing domain adaptation (DA) paradigms like general DA and source-free DA for 3D HPE overlook the issues of non-stationary target pose datasets. To address these challenges, we propose a novel task named lifelong domain adaptive 3D HPE. To our knowledge, we are the first to introduce the lifelong domain adaptation to the 3D HPE task. In this lifelong DA setting, the pose estimator is pretrained on the source domain and subsequently adapted to distinct target domains. Moreover, during adaptation to the current target domain, the pose estimator cannot access the source and all the previous target domains. The lifelong DA for 3D HPE involves overcoming challenges in adapting to current domain poses and preserving knowledge from previous domains, particularly combating catastrophic forgetting. We present an innovative Generative Adversarial Network (GAN) framework, which incorporates 3D pose generators, a 2D pose discriminator, and a 3D pose estimator. This framework effectively mitigates domain shifts and aligns original and augmented poses. Moreover, we construct a novel 3D pose generator paradigm, integrating pose-aware, temporal-aware, and domain-aware knowledge to enhance the current domain's adaptation and alleviate catastrophic forgetting on previous domains. Our method demonstrates superior performance through extensive experiments on diverse domain adaptive 3D HPE datasets.

preprint2026arXiv

Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning

Mixture-of-experts variants of parameter-efficient fine-tuning enable per-token specialization, but they introduce additional trainable routers and expert parameters, increasing memory usage and training cost. This undermines the core goal of parameter-efficient fine-tuning. We propose Monkey Jump, a method that brings mixture-of-experts-style specialization to parameter-efficient fine-tuning without introducing extra trainable parameters for experts or routers. Instead of adding new adapters as experts, Monkey Jump treats the adapters already present in each Transformer block (such as query, key, value, up, and down projections) as implicit experts and routes tokens among them. Routing is performed using k-means clustering with exponentially moving averaged cluster centers, requiring no gradients and no learned parameters. We theoretically show that token-wise routing increases expressivity and can outperform shared adapters by avoiding cancellation effects. Across multi-task experiments covering 14 text, 14 image, and 19 video benchmarks, Monkey Jump achieves competitive performance with mixture-of-experts-based parameter-efficient fine-tuning methods while using 7 to 29 times fewer trainable parameters, up to 48 percent lower memory consumption, and 1.5 to 2 times faster training. Monkey Jump is architecture-agnostic and can be applied to any adapter-based parameter-efficient fine-tuning method.

preprint2026arXiv

MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion

Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modality missing, where an entire channel is absent, and within-modality missing, where a contiguous time segment is lost. No existing benchmark evaluates multiple fusion architectures under both failure modes at controlled severity levels across diverse clinical datasets. We present MuteBench, a benchmark covering 9 datasets from 7 clinical domains, 6 fusion architectures, and 2 missing-data modes over 125,000 samples. Through this benchmark, we find that architecture family is the strongest predictor of robustness, outweighing parameter count. Channel-independent models tolerate modality missing well but can be sensitive to within-modality missing, especially on short sequences. Curriculum modality dropout protects reliably only up to the maximum dropout rate used in training. We also find that channel count, sequence length, and modality alignment jointly determine which failure mode poses the greater threat. Finally, a PTB-XL case study suggests that diffusion-based imputation can improve downstream classification under within-modality missing, with the largest gains for models whose expert routing is most sensitive to corrupted inputs, though broader validation across datasets remains an open direction. MuteBench provides practitioners with concrete guidance for both selecting existing architectures and informing the design of future robust multimodal fusion methods.

preprint2026arXiv

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding

Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes inference expensive. This cost can be reduced spatially by unmasking multiple tokens per step, or temporally by collapsing multiple denoising steps into one verification call. We propose Parallel Speculative Decoding (PSD), a training-free framework that jointly improves inference along both axes. Using the confidence scores from a single forward pass, PSD selects positions to unmask via a configurable, adaptive unmasking policy and constructs multi-depth speculative drafts without extra model calls. A final batched verification pass then applies hierarchical acceptance, keeping the deepest draft that remains consistent with the updated predictions. Experiments on three dLLMs across reasoning and code generation tasks show that PSD achieves favorable trade-offs between inference efficiency and generation quality, reaching up to $5.5\times$ tokens per forward pass with accuracy comparable to greedy decoding.

preprint2026arXiv

Random Batch Sum-of-Gaussians Method for Molecular Dynamics of Born-Mayer-Huggins Systems

The Born-Mayer-Huggins (BMH) potential, which combines Coulomb interactions with dispersion and short-range exponential repulsion, is widely used for ionic materials such as molten salts. However, large-scale molecular dynamics simulations of BMH systems are often limited by computation, communication, and memory costs. We recently proposed the random batch sum-of-Gaussians (RBSOG) method, which accelerates Coulomb calculations by using a sum-of-Gaussians (SOG) decomposition to split the potential into short- and long-range parts and by applying importance sampling in Fourier space for the long-range part. In this work, we extend the RBSOG to BMH systems and incorporate a random batch list (RBL) scheme to further accelerate the short-range part, yielding a unified framework for efficient simulations with the BMH potential. The combination of the SOG decomposition and the RBL enables an efficient and scalable treatment of both long- and short-range interactions in BMH system, particularly the RBL well handles the medium-range exponential repulsion and dispersion by the random batch neighbor list. Error estimate is provided to show the theoretical convergence of the RBL force. We evaluate the framework on molten NaCl and mixed alkali halide with up to $5\times10^6$ atoms on $2048$ CPU cores. Compared to the Ewald-based particle-particle particle-mesh method and the RBSOG-only method, our method achieves approximately $4\sim10\times$ and $2\times$ speedups while using $1000$ cores, respectively, under the same level of structural and thermodynamic accuracy and with a reduced memory usage. These results demonstrate the attractive performance of our method in accuracy and scalability for MD simulations with long-range interactions.

preprint2026arXiv

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture broad semantics and later tokens refine them. Recent work augments this paradigm with reasoning traces and optimizes them via reinforcement learning with verifiable rewards, typically outcome-reward algorithm with exact-match feedback on the generated SID. However, in large-catalog recommendation, exact-match feedback on the generated SID only reports whether the final item is correct; when a generated SID mismatches, outcome-reward cannot identify which SID-token prediction caused the mismatch and may penalize matched SID-token positions together with the mismatched position. We identify that the natural unit of credit assignment in this setting is a single reasoning step (one thinking block paired with one SID token). We instantiate this idea in SAPO (Step-Aligned Policy Optimization): rather than broadcasting one advantage to the whole response, SAPO computes a separate group-relative advantage for each reasoning step and applies it only to the corresponding thinking block and SID token. Across three real-world recommendation datasets, SAPO stabilizes reinforcement-learning training and consistently improves over existing generative recommendation baselines, with the largest gains where sparse exact-match feedback makes reasoning-step credit assignment important. Our results suggest that reinforcement-learning objectives for structured generation should mirror the decoder's own decomposition of the output.

preprint2026arXiv

Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution

Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To improve overall efficiency, existing methods often rely on aggressive graph evolution among agents (e.g., node or edge pruning), which risks prematurely discarding valuable agents due to transient issues such as hallucinations or temporary knowledge gaps. However, such hard pruning overlooks the potential for ``zombie'' agents to recover and contribute in subsequent discussion rounds. In this paper, we propose AgentRevive, a Markov state-aware framework for resilient multi-agent evolution. Our approach dynamically manages agent collaboration through soft state transitions, implemented via two key components: (1) State-Aware Policy Learning: Agent states are divided into ``Active'', ``Standby'', and ``Terminated'' states, selectively propagating messages based on agent memory. The policy employs a risk estimator to optimize agent state transitions by assessing hallucination risk, minimizing the influence of unreliable nodes while safeguarding valuable ones. (2) State-Aware Edge Optimization: Subgraph edges are pruned according to states learned from the policy, permanently removing ``Terminated'' nodes and retaining ``Standby'' nodes for subsequent rounds to assess their potential future contributions. Extensive experiments on general reasoning, domain-specific, and hallucination challenge tasks show that our method consistently outperforms strong baselines and significantly reduces token consumption through state-aware agent scheduling.

preprint2026arXiv

Universal Graph Backdoor Defense: A Feature-based Homophily Perspective

Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) poses a significant barrier to broader adoption in high-stakes applications. Despite recent advances in graph backdoor defense (GBD), existing methods primarily focus on subgraph-based GBAs, relying on the assumption that poisoned target nodes are explicitly connected to subgraph triggers. Our empirical results reveal that such structure-centric approaches fail to defend against emerging feature-based GBAs that preserve graph topology. Therefore, in this paper, we study a novel problem of universal graph backdoor defense. First, we investigate the shared effects of both attack types from a feature-based homophily perspective, which characterizes local feature consistency between nodes and their neighborhoods. Thorough theoretical and empirical analyses demonstrate that, regardless of trigger mechanisms, backdoors induced by GBAs exhibit lower feature-based homophily than clean nodes, indicating a discrepancy in local feature similarity. Motivated by this insight, we propose to leverage node-level local feature consistency, modeled by a neighbor-aware reconstruction loss, to distinguish backdoors from clean nodes. Then, a robust training strategy is developed to eliminate trigger effects while reducing noise induced by detection uncertainty. Extensive experiments demonstrate that our framework significantly degrades the attack success rate and maintains competitive clean accuracy under both subgraph-based and feature-based attacks.

preprint2026arXiv

VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing

Real-world video editing demands not only expert knowledge of cinematic techniques but also multimodal reasoning to select, align, and combine footage into coherent narratives. While recent Large Multimodal Models (LMMs) have shown remarkable progress in general video understanding, their abilities in multi-video reasoning and operational editing workflows remain largely unexplored. We introduce VEBENCH, the first comprehensive benchmark designed to evaluate both editing knowledge understanding and operational reasoning in realistic video editing scenarios. VEBENCH contains 3.9K high-quality edited videos (over 257 hours) and 3,080 human-verified QA pairs, built through a three-round human-AI collaborative annotation pipeline that ensures precise temporal labeling and semantic consistency. It features two complementary QA tasks: 1) Video Editing Technique Recognition, assessing models' ability to identify 7 editing techniques using multimodal cues; and 2) Video Editing Operation Simulation, modeling real-world editing workflows by requiring the selection and temporal localization of relevant clips from multiple candidates. Extensive experiments across proprietary (e.g., Gemini-2.5-Pro) and open-source LMMs reveal a large gap between current model performance and human-level editing cognition. These results highlight the urgent need for bridging video understanding with creative operational reasoning. We envision VEBENCH as a foundation for advancing intelligent video editing systems and driving future research on complex reasoning.

preprint2025arXiv

Axially Deformed Proton-Neutron Relativistic Quasiparticle Finite Amplitude Method for Charge-Exchange Transitions

The quasiparticle finite amplitude method (QFAM) is extended to describe charge-exchange transitions based on the relativistic Hartree-Bogoliubov model, adopting the point-coupling energy density functional DD-PC1 and a finite-range separable pairing force. After validation through comparison with relativistic quasiparticle random-phase approximation (QRPA) results in spherical nuclei, the deformation effects on isobaric analog resonances (IAR) and Gamow-Teller (GT) transitions in Zn isotopes are investigated. The GT strength exhibits significant fragmentation in deformed nuclei. The analysis of summed strengths and centroid energies in GT resonance region between the $K=0$ and $K=1$ components reveals that prolate configurations exhibit stronger $K=1$ strength and lower $K=1$ centroid energy, while oblate shapes show an opposite behavior, with stronger $K=0$ strength and lower $K=0$ energy. The effects of isoscalar pairing on GT strength distributions for different shape configurations are also examined.

preprint2024arXiv

Independence in the Home: A Wearable Interface for a Person with Quadriplegia to Teleoperate a Mobile Manipulator

Teleoperation of mobile manipulators within a home environment can significantly enhance the independence of individuals with severe motor impairments, allowing them to regain the ability to perform self-care and household tasks. There is a critical need for novel teleoperation interfaces to offer effective alternatives for individuals with impairments who may encounter challenges in using existing interfaces due to physical limitations. In this work, we iterate on one such interface, HAT (Head-Worn Assistive Teleoperation), an inertial-based wearable integrated into any head-worn garment. We evaluate HAT through a 7-day in-home study with Henry Evans, a non-speaking individual with quadriplegia who has participated extensively in assistive robotics studies. We additionally evaluate HAT with a proposed shared control method for mobile manipulators termed Driver Assistance and demonstrate how the interface generalizes to other physical devices and contexts. Our results show that HAT is a strong teleoperation interface across key metrics including efficiency, errors, learning curve, and workload. Code and videos are located on our project website.

preprint2024arXiv

Language-Assisted Deep Learning for Autistic Behaviors Recognition

Correctly recognizing the behaviors of children with Autism Spectrum Disorder (ASD) is of vital importance for the diagnosis of Autism and timely early intervention. However, the observation and recording during the treatment from the parents of autistic children may not be accurate and objective. In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent. Existing human action recognition models can now achieve persuasive performance on challenging activity datasets, e.g. daily activity, and sports activity. However, problem behaviors in children with ASD are very different from these general activities, and recognizing these problem behaviors via computer vision is less studied. In this paper, we first evaluate a strong baseline for action recognition, i.e. Video Swin Transformer, on two autism behaviors datasets (SSBD and ESBD) and show that it can achieve high accuracy and outperform the previous methods by a large margin, demonstrating the feasibility of vision-based problem behaviors recognition. Moreover, we propose language-assisted training to further enhance the action recognition performance. Specifically, we develop a two-branch multimodal deep learning framework by incorporating the "freely available" language description for each type of problem behavior. Experimental results demonstrate that incorporating additional language supervision can bring an obvious performance boost for the autism problem behaviors recognition task as compared to using the video information only (i.e. 3.49% improvement on ESBD and 1.46% on SSBD).

preprint2024arXiv

Noise-Aware Speech Separation with Contrastive Learning

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background noise to each speaker. In this paper, we propose a noise-aware SS (NASS) method, which aims to improve the speech quality for separated signals under noisy conditions. Specifically, NASS views background noise as an additional output and predicts it along with other speakers in a mask-based manner. To effectively denoise, we introduce patch-wise contrastive learning (PCL) between noise and speaker representations from the decoder input and encoder output. PCL loss aims to minimize the mutual information between predicted noise and other speakers at multiple-patch level to suppress the noise information in separated signals. Experimental results show that NASS achieves 1 to 2dB SI-SNRi or SDRi over DPRNN and Sepformer on WHAM! and LibriMix noisy datasets, with less than 0.1M parameter increase.

preprint2024arXiv

Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptation

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image samples in the embedding space. However, existing proxy-based DML methods focus on learning individual proxy-to-sample distance while the overall distribution of samples and proxies lacks attention. In this paper, we present a novel proxy-based DML framework that focuses on aligning the sample and proxy distributions to improve the efficiency of proxy-based DML losses. Specifically, we propose the Data-Augmented Domain Adaptation (DADA) method to adapt the domain gap between the group of samples and proxies. To the best of our knowledge, we are the first to leverage domain adaptation to boost the performance of proxy-based DML. We show that our method can be easily plugged into existing proxy-based DML losses. Our experiments on benchmarks, including the popular CUB-200-2011, CARS196, Stanford Online Products, and In-Shop Clothes Retrieval, show that our learning algorithm significantly improves the existing proxy losses and achieves superior results compared to the existing methods.

preprint2024arXiv

UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite

In the nascent domain of urban digital twins (UDT), the prospects for leveraging cutting-edge deep learning techniques are vast and compelling. Particularly within the specialized area of intelligent road inspection (IRI), a noticeable gap exists, underscored by the current dearth of dedicated research efforts and the lack of large-scale well-annotated datasets. To foster advancements in this burgeoning field, we have launched an online open-source benchmark suite, referred to as UDTIRI. Along with this article, we introduce the road pothole detection task, the first online competition published within this benchmark suite. This task provides a well-annotated dataset, comprising 1,000 RGB images and their pixel/instance-level ground-truth annotations, captured in diverse real-world scenarios under different illumination and weather conditions. Our benchmark provides a systematic and thorough evaluation of state-of-the-art object detection, semantic segmentation, and instance segmentation networks, developed based on either convolutional neural networks or Transformers. We anticipate that our benchmark will serve as a catalyst for the integration of advanced UDT techniques into IRI. By providing algorithms with a more comprehensive understanding of diverse road conditions, we seek to unlock their untapped potential and foster innovation in this critical domain.

preprint2023arXiv

Few-shot Node Classification with Extremely Weak Supervision

Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremely limited labeled nodes for meta-training, the generalization gap between meta-training and meta-test will become larger and thus lead to suboptimal performance. To tackle this issue, we study a novel problem of few-shot node classification with extremely weak supervision and propose a principled framework X-FNC under the prevalent meta-learning framework. Specifically, our goal is to accumulate meta-knowledge across different meta-training tasks with extremely weak supervision and generalize such knowledge to meta-test tasks. To address the challenges resulting from extremely scarce labeled nodes, we propose two essential modules to obtain pseudo-labeled nodes as extra references and effectively learn from extremely limited supervision information. We further conduct extensive experiments on four node classification datasets with extremely weak supervision to validate the superiority of our framework compared to the state-of-the-art baselines.

preprint2023arXiv

Machine Learning-Based Secret Key Generation for IRS-assisted Multi-antenna Systems

Physical-layer key generation (PKG) based on wireless channels is a lightweight technique to establish secure keys between legitimate communication nodes. Recently, intelligent reflecting surfaces (IRSs) have been leveraged to enhance the performance of PKG in terms of secret key rate (SKR), as it can reconfigure the wireless propagation environment and introduce more channel randomness. In this paper, we investigate an IRS-assisted PKG system, taking into account the channel spatial correlation at both the base station (BS) and the IRS. Based on the considered system model, the closed form expression of SKR is derived analytically. Aiming to maximize the SKR, a joint design problem of the BS precoding matrix and the IRS reflecting coefficient vector is formulated. To address this high-dimensional non-convex optimization problem, we propose a novel unsupervised deep neural network (DNN) based algorithm with a simple structure. Different from most previous works that adopt the iterative optimization to solve the problem, the proposed DNN based algorithm directly obtains the BS precoding and IRS phase shifts as the output of the DNN. Simulation results reveal that the proposed DNN-based algorithm outperforms the benchmark methods with regard to SKR.

preprint2023arXiv

Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning

In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is continually updated and the induced distribution over visited states used for model learning shifts accordingly. Prior methods alleviate this issue by quantifying the uncertainty of model-generated samples. However, these methods only quantify the uncertainty passively after the samples were generated, rather than foreseeing the uncertainty before model trajectories fall into those highly uncertain regions. The resulting low-quality samples can induce unstable learning targets and hinder the optimization of the policy. Moreover, while being learned to minimize one-step prediction errors, the model is generally used to predict for multiple steps, leading to a mismatch between the objectives of model learning and model usage. To this end, we propose \emph{Plan To Predict} (P2P), an MBRL framework that treats the model rollout process as a sequential decision making problem by reversely considering the model as a decision maker and the current policy as the dynamics. In this way, the model can quickly adapt to the current policy and foresee the multi-step future uncertainty when generating trajectories. Theoretically, we show that the performance of P2P can be guaranteed by approximately optimizing a lower bound of the true environment return. Empirical results demonstrate that P2P achieves state-of-the-art performance on several challenging benchmark tasks.

preprint2022arXiv

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

Existing deep learning-based human mesh reconstruction approaches have a tendency to build larger networks in order to achieve higher accuracy. Computational complexity and model size are often neglected, despite being key characteristics for practical use of human mesh reconstruction models (e.g. virtual try-on systems). In this paper, we present GTRS, a lightweight pose-based method that can reconstruct human mesh from 2D human pose. We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh. We demonstrate the efficiency and generalization of GTRS by extensive evaluations on the Human3.6M and 3DPW datasets. In particular, GTRS achieves better accuracy than the SOTA pose-based method Pose2Mesh while only using 10.2% of the parameters (Params) and 2.5% of the FLOPs on the challenging in-the-wild 3DPW dataset. Code will be publicly available.

preprint2022arXiv

A Material-based Panspermia Hypothesis: The Potential of Polymer Gels and Membraneless Droplets

The Panspermia hypothesis posits that either life's building blocks (molecular Panspermia) or life itself (organism-based Panspermia) may have been interplanetary transferred to facilitate the Origins of Life (OoL) on a given planet, complementing several current OoL frameworks. Although many spaceflight experiments were performed in the past to test for potential terrestrial organisms as Panspermia seeds, it is uncertain whether such organisms will likely "seed" a new planet even if they are able to survive spaceflight. Therefore, rather than using organisms, using abiotic chemicals as seeds has been proposed as part of the molecular Panspermia hypothesis. Here, as an extension of this hypothesis, we introduce and review the plausibility of a polymeric material-based Panspermia seed (M-BPS) theoretical concept, where the type of polymeric material that can function as a M-BPS must be able to: 1) survive spaceflight, and 2) "function", i.e., contingently drive chemical evolution towards some form of abiogenesis once arriving on a foreign planet. We use polymeric gels as a model example of a potential M-BPS. Polymeric gels that can be prebiotically synthesized on one planet (such as polyester gels) could be transferred to another planet via meteoritic transfer, where upon landing on a liquid bearing planet, can assemble into structures containing cellular-like characteristics and functionalities. Such features presupposed that these gels can assemble into compartments through phase separation to accomplish relevant functions such as encapsulation of primitive metabolic, genetic and catalytic materials, exchange of these materials, motion, coalescence, and evolution. All of these functions can result in the gels' capability to alter local geochemical niches on other planets, thereby allowing chemical evolution to lead to OoL events.

preprint2022arXiv

A quasar shedding its dust cocoon at redshift 2

We present the first near-IR spectroscopy and joint analyses of multi-wavelength observations for SDSS J082747.14+425241.1, a dust-reddened, weak broad emission-line quasar (WLQ) undergoing a remarkable broad absorption line (BAL) transformation. The systemic redshift is more precisely measured to be $z=2.070\pm0.001$ using H$β$ compared to $z=2.040\pm0.003$ using \mgii\ from the literature, signifying an extreme \mgii\ blueshift of $2140\pm530$ \kms\ relative to H$β$. Using the H$β$-based single-epoch scaling relation with a systematic uncertainty of 0.3 dex, its black hole (BH) mass and Eddington ratio are estimated to be $M_{\rm BH}\sim6.1\times10^8M_\odot$ and $λ_{\rm Edd}\sim0.71$, indicative of being in a rapidly accreting phase. Our investigations confirm the WLQ nature and the LoBAL$\rightarrow$HiBAL transformation, along with a factor of 2 increase in the \mgii+\feii\ emission strength and a decrease of 0.1 in $E(B-V)$ over two decades. The kinetic power of this LoBAL wind at $R\sim$15 pc from its BH is estimated to be $\sim$43\% of the Eddington luminosity, sufficient for quasar feedback upon its host galaxy albeit with an order-of-magnitude uncertainty. This quasar provides a clear example of the long-sought scenario where LoBAL quasars are surrounded by dust cocoons, and wide-angle nuclear winds play a key role in the transition for red quasars evolving into the commonly seen blue quasars.

preprint2022arXiv

An Analysis of Deep Reinforcement Learning Agents for Text-based Games

Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge. Finding TBG agent deep learning modules' performance in standardized environments, and testing their performance among different evaluation types is also important for TBG agent research. We constructed a standardized TBG agent with no hand-crafted rules, formally categorized TBG evaluation types, and analyzed selected methods in our environment.

preprint2022arXiv

Annotating Columns with Pre-trained Language Models

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information. In this paper, we study the problem of annotating table columns (i.e., predicting column types and the relationships between columns) using only information from the table itself. We develop a multi-task learning framework (called Doduo) based on pre-trained language models, which takes the entire table as input and predicts column types/relations using a single model. Experimental results show that Doduo establishes new state-of-the-art performance on two benchmarks for the column type prediction and column relation prediction tasks with up to 4.0% and 11.9% improvements, respectively. We report that Doduo can already outperform the previous state-of-the-art performance with a minimal number of tokens, only 8 tokens per column. We release a toolbox (https://github.com/megagonlabs/doduo) and confirm the effectiveness of Doduo on a real-world data science problem through a case study.

preprint2022arXiv

Attention guided global enhancement and local refinement network for semantic segmentation

The encoder-decoder architecture is widely used as a lightweight semantic segmentation network. However, it struggles with a limited performance compared to a well-designed Dilated-FCN model for two major problems. First, commonly used upsampling methods in the decoder such as interpolation and deconvolution suffer from a local receptive field, unable to encode global contexts. Second, low-level features may bring noises to the network decoder through skip connections for the inadequacy of semantic concepts in early encoder layers. To tackle these challenges, a Global Enhancement Method is proposed to aggregate global information from high-level feature maps and adaptively distribute them to different decoder layers, alleviating the shortage of global contexts in the upsampling process. Besides, a Local Refinement Module is developed by utilizing the decoder features as the semantic guidance to refine the noisy encoder features before the fusion of these two (the decoder features and the encoder features). Then, the two methods are integrated into a Context Fusion Block, and based on that, a novel Attention guided Global enhancement and Local refinement Network (AGLN) is elaborately designed. Extensive experiments on PASCAL Context, ADE20K, and PASCAL VOC 2012 datasets have demonstrated the effectiveness of the proposed approach. In particular, with a vanilla ResNet-101 backbone, AGLN achieves the state-of-the-art result (56.23% mean IoU) on the PASCAL Context dataset. The code is available at https://github.com/zhasen1996/AGLN.

preprint2022arXiv

BANet: Motion Forecasting with Boundary Aware Network

We propose a motion forecasting model called BANet, which means Boundary-Aware Network, and it is a variant of LaneGCN. We believe that it is not enough to use only the lane centerline as input to obtain the embedding features of the vector map nodes. The lane centerline can only provide the topology of the lanes, and other elements of the vector map also contain rich information. For example, the lane boundary can provide traffic rule constraint information such as whether it is possible to change lanes which is very important. Therefore, we achieved better performance by encoding more vector map elements in the motion forecasting model.We report our results on the 2022 Argoverse2 Motion Forecasting challenge and rank 1st on the test leaderboard.

preprint2022arXiv

Binary Representation via Jointly Personalized Sparse Hashing

Unsupervised hashing has attracted much attention for binary representation learning due to the requirement of economical storage and efficiency of binary codes. It aims to encode high-dimensional features in the Hamming space with similarity preservation between instances. However, most existing methods learn hash functions in manifold-based approaches. Those methods capture the local geometric structures (i.e., pairwise relationships) of data, and lack satisfactory performance in dealing with real-world scenarios that produce similar features (e.g. color and shape) with different semantic information. To address this challenge, in this work, we propose an effective unsupervised method, namely Jointly Personalized Sparse Hashing (JPSH), for binary representation learning. To be specific, firstly, we propose a novel personalized hashing module, i.e., Personalized Sparse Hashing (PSH). Different personalized subspaces are constructed to reflect category-specific attributes for different clusters, adaptively mapping instances within the same cluster to the same Hamming space. In addition, we deploy sparse constraints for different personalized subspaces to select important features. We also collect the strengths of the other clusters to build the PSH module with avoiding over-fitting. Then, to simultaneously preserve semantic and pairwise similarities in our JPSH, we incorporate the PSH and manifold-based hash learning into the seamless formulation. As such, JPSH not only distinguishes the instances from different clusters, but also preserves local neighborhood structures within the cluster. Finally, an alternating optimization algorithm is adopted to iteratively capture analytical solutions of the JPSH model. Extensive experiments on four benchmark datasets verify that the JPSH outperforms several hashing algorithms on the similarity search task.

preprint2022arXiv

Category Guided Attention Network for Brain Tumor Segmentation in MRI

Objective: Magnetic resonance imaging (MRI) has been widely used for the analysis and diagnosis of brain diseases. Accurate and automatic brain tumor segmentation is of paramount importance for radiation treatment. However, low tissue contrast in tumor regions makes it a challenging task.Approach: We propose a novel segmentation network named Category Guided Attention U-Net (CGA U-Net). In this model, we design a Supervised Attention Module (SAM) based on the attention mechanism, which can capture more accurate and stable long-range dependency in feature maps without introducing much computational cost. Moreover, we propose an intra-class update approach to reconstruct feature maps by aggregating pixels of the same category. Main results: Experimental results on the BraTS 2019 datasets show that the proposed method outperformers the state-of-the-art algorithms in both segmentation performance and computational complexity. Significance: The CGA U-Net can effectively capture the global semantic information in the MRI image by using the SAM module, while significantly reducing the computational cost. Code is available at https://github.com/delugewalker/CGA-U-Net.

preprint2022arXiv

Composition of low-lying $\mathbf{J=\tfrac{3}{2}^\pm \,Δ}$-baryons

A Poincaré-covariant quark+diquark Faddeev equation is used to develop insights into the structure of the four lightest $(I,J^P=\tfrac{3}{2},\tfrac{3}{2}^\pm)$ baryon multiplets. Whilst these systems can contain isovector-axialvector and isovector-vector diquarks, one may neglect the latter and still arrive at a reliable description. The $(\tfrac{3}{2},\tfrac{3}{2}^+)$ states are the simpler systems, with features that bear some resemblance to quark model pictures, \emph{e.g}., their most prominent rest-frame orbital angular momentum component is $\mathsf S$-wave and the $Δ(1600)\tfrac{3}{2}^+$ may reasonably be viewed as a radial excitation of the $Δ(1232)\tfrac{3}{2}^+$. The $(\tfrac{3}{2},\tfrac{3}{2}^-)$ states are more complex: the $Δ(1940)\tfrac{3}{2}^-$ expresses little of the character of a radial excitation of the $Δ(1700)\tfrac{3}{2}^-$; and whilst the rest-frame wave function of the latter is predominantly $\mathsf P$-wave, the leading piece in the $Δ(1940)\tfrac{3}{2}^-$ wave function is $\mathsf S$-wave, in conflict with quark model expectations. Experiments that can test these predictions, such as large momentum transfer resonance electroexcitation, may shed light on the nature of emergent hadron mass.

preprint2022arXiv

Consistency-based Active Learning for Object Detection

Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data. CALD has three appealing benefits. (i) CALD is systematically designed by investigating the weaknesses of existing active learning methods, which do not take the unique challenges of object detection into account. (ii) CALD unifies box regression and classification with a single metric, which is not concerned by active learning methods for classification. CALD also focuses on the most informative local region rather than the whole image, which is beneficial for object detection. (iii) CALD not only gauges individual information for sample selection, but also leverages mutual information to encourage a balanced data distribution. Extensive experiments show that CALD significantly outperforms existing state-of-the-art task-agnostic and detection-specific active learning methods on general object detection datasets. Based on the Faster R-CNN detector, CALD consistently surpasses the baseline method (random selection) by 2.9/2.8/0.8 mAP on average on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO. Code is available at \url{https://github.com/we1pingyu/CALD}

preprint2022arXiv

Cross-mode Stabilized Stochastic Shallow Water Systems Using Stochastic Finite Element Methods

The development of surrogate models to study uncertainties in hydrologic systems requires significant effort in the development of sampling strategies and forward model simulations. Furthermore, in applications where prediction time is critical, such as prediction of hurricane storm surge, the predictions of system response and uncertainties can be required within short time frames. Here, we develop an efficient stochastic shallow water model to address these issues. To discretize the physical and probability spaces we use a Stochastic Galerkin method and a Incremental Pressure Correction scheme to advance the solution in time. To overcome discrete stability issues, we propose cross-mode stabilization methods which employs existing stabilization methods in the probability space by adding stabilization terms to every stochastic mode in a modes-coupled way. We extensively verify the developed method for both idealized shallow water test cases and hindcasting of past hurricanes. We subsequently use the developed and verified method to perform a comprehensive statistical analysis of the established shallow water surrogate models. Finally, we propose a predictor for hurricane storm surge under uncertain wind drag coefficients and demonstrate its effectivity for Hurricanes Ike and Harvey.

preprint2022arXiv

Deep Reinforcement Learning Coordinated Receiver Beamforming for Millimeter-Wave Train-ground Communications

As more and more people choose high-speed rail (HSR) as a means of transportation for short trips, there is ever growing demand of high quality of multimedia services. With its rich spectrum resources, millimeter wave (mm-wave) communications can satisfy the high network capacity requirements for HSR. Also, it is possible for receivers (RXs) to be equipped with antenna arrays in mm-wave communication systems due to its short wavelength. However, as HSRs run with high speed, the received signal power (RSP) varies rapidly over a cell and it is the lowest at the edge of the cell compared to other locations. Consequently, it is necessary to conduct research on RX beamforming for HSR in mm-wave band to improve the quality of the received signal. In this paper, we focus on RX beamforming for a mm-wave train-ground communication system. To improve the RSP, we propose an effective RX beamforming scheme based on deep reinforcement learning (DRL), and develop a deep Q-network (DQN) algorithm to train and determine the optimal RX beam direction with the purpose of maximizing average RSP. Through extensive simulations, we demonstrate that the proposed scheme has better performance than the four baseline schemes in terms of average RSP at most positions on the railway.

preprint2022arXiv

EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge

Federated learning (FL) is a distributed machine learning technology for next-generation AI systems that allows a number of workers, i.e., edge devices, collaboratively learn a shared global model while keeping their data locally to prevent privacy leakage. Enabling FL over wireless multi-hop networks can democratize AI and make it accessible in a cost-effective manner. However, the noisy bandwidth-limited multi-hop wireless connections can lead to delayed and nomadic model updates, which significantly slows down the FL convergence speed. To address such challenges, this paper aims to accelerate FL convergence over wireless edge by optimizing the multi-hop federated networking performance. In particular, the FL convergence optimization problem is formulated as a Markov decision process (MDP). To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i.e., workers) and the remote server. To validate the proposed solutions, FedEdge is developed and implemented, which is the first experimental framework in the literature for FL over multi-hop wireless edge computing networks. FedEdge allows us to fast prototype, deploy, and evaluate novel FL algorithms along with RL-based system optimization methods in real wireless devices. Moreover, a physical experimental testbed is implemented by customizing the widely adopted Linux wireless routers and ML computing nodes.Finally, our experimentation results on the testbed show that the proposed network-accelerated FL system can practically and significantly improve FL convergence speed, compared to the FL system empowered by the production-grade commercially available wireless networking protocol, BATMAN-Adv.

preprint2022arXiv

Embedding Gradient-based Optimization in Image Registration Networks

Deep learning (DL) image registration methods amortize the costly pair-wise iterative optimization by training deep neural networks to predict the optimal transformation in one fast forward-pass. In this work, we bridge the gap between traditional iterative energy optimization-based registration and network-based registration, and propose Gradient Descent Network for Image Registration (GraDIRN). Our proposed approach trains a DL network that embeds unrolled multiresolution gradient-based energy optimization in its forward pass, which explicitly enforces image dissimilarity minimization in its update steps. Extensive evaluations were performed on registration tasks using 2D cardiac MR and 3D brain MR images. We demonstrate that our approach achieved state-of-the-art registration performance while using fewer learned parameters, with good data efficiency and domain robustness.

preprint2022arXiv

Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation

The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impractical due to data sharing and privacy issues. To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation tasks. AdvChain augments data with dynamic data augmentation, generating randomly chained photo-metric and geometric transformations to resemble realistic yet challenging imaging variations to expand training data. By jointly optimizing the data augmentation model and a segmentation network during training, challenging examples are generated to enhance network generalizability for the downstream task. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. It is computationally efficient and applicable for both low-shot supervised and semi-supervised learning. We analyze and evaluate the method on two MR image segmentation tasks: cardiac segmentation and prostate segmentation with limited labeled data. Results show that the proposed approach can alleviate the need for labeled data while improving model generalization ability, indicating its practical value in medical imaging applications.

preprint2022arXiv

Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores

Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift. If we could estimate the performance that a pre-trained model would achieve on data from a specific deployment setting, for example a certain clinic, we could judge whether the model could safely be deployed or if its performance degrades unacceptably on the specific data. Existing approaches estimate this based on the confidence of predictions made on unlabeled test data from the deployment's domain. We find existing methods struggle with data that present class imbalance, because the methods used to calibrate confidence do not account for bias induced by class imbalance, consequently failing to estimate class-wise accuracy. Here, we introduce class-wise calibration within the framework of performance estimation for imbalanced datasets. Specifically, we derive class-specific modifications of state-of-the-art confidence-based model evaluation methods including temperature scaling (TS), difference of confidences (DoC), and average thresholded confidence (ATC). We also extend the methods to estimate Dice similarity coefficient (DSC) in image segmentation. We conduct experiments on four tasks and find the proposed modifications consistently improve the estimation accuracy for imbalanced datasets. Our methods improve accuracy estimation by 18\% in classification under natural domain shifts, and double the estimation accuracy on segmentation tasks, when compared with prior methods.

preprint2022arXiv

Evidence for quasar fast outflows being accelerated at the scale of tens of parsecs

Quasar outflows may play a crucial role in regulating the host galaxy, although the spatial scale of quasar outflows remain a major enigma, with their acceleration mechanism poorly understood. The kinematic information of outflow is the key to understanding its origin and acceleration mechanism. Here, we report the galactocentric distances of different outflow components for both a sample and an individual quasar. We find that the outflow distance increases with velocity, with a typical value from several parsecs to more than one hundred parsecs, providing direct evidence for an acceleration happening at a scale of the order of 10 parsecs. These outflows carry ~1% of the total quasar energy, while their kinematics are consistent with a dust driven model with a launching radius comparable to the scale of a dusty torus, indicating that the coupling between dust and quasar radiation may produce powerful feedback that is crucial to galaxy evolution.

preprint2022arXiv

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to graph classes with limited labeled graphs. Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set. However, existing methods generally ignore task correlations among meta-training tasks while treating them independently. Nevertheless, such task correlations can advance the model generalization to the target task for better classification performance. On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. Then we further design a loss-based sampling strategy to select tasks with more correlated classes. Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification. Extensive experiments on four prevalent few-shot graph classification datasets demonstrate the superiority of FAITH over other state-of-the-art baselines.

preprint2022arXiv

Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network

Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improve the performance. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance on lots of benchmarks, i.e., ActivityNet-1.3 (40.01% mAP), HACS Segments (38.39% mAP), SoccerNet-Action Spotting (54.09% mAP). It outperforms existing single-network detector by a large margin.

preprint2022arXiv

Fog Based Computation Offloading for Swarm of Drones

Due to the limited computing resources of swarm of drones, it is difficult to handle computation-intensive tasks locally, hence the cloud based computation offloading is widely adopted. However, for the business which requires low latency and high reliability, the cloud-based solution is not suitable, because of the slow response time caused by long distance data transmission. Therefore, to solve the problem mentioned above, in this paper, we introduce fog computing into swarm of drones (FCSD). Focusing on the latency and reliability sensitive business scenarios, the latency and reliability is constructed as the constraints of the optimization problem. And in order to enhance the practicality of the FCSD system, we formulate the energy consumption of FCSD as the optimization target function, to decrease the energy consumption as far as possible, under the premise of satisfying the latency and reliability requirements of the task. Furthermore, a heuristic algorithm based on genetic algorithm is designed to perform optimal task allocation in FCSD system. The simulation results validate that the proposed fog based computation offloading with the heuristic algorithm can complete the computing task effectively with the minimal energy consumption under the requirements of latency and reliability.

preprint2022arXiv

Full-scale validation of CFD simulations of buoyancy-driven ventilation in a three-story office building

Computational fluid dynamics (CFD) is frequently used to support the design of naturally ventilated buildings; however, the model accuracy should be thoroughly assessed, ideally through validation with full-scale measurements. The present study aims to (1) validate transient CFD simulations with uncertainty quantification (UQ) for buoyancy-driven natural ventilation against full-scale experiments in an operational atrium building, and (2) quantify the sensitivity of the CFD results to the thermal boundary conditions. The UQ and sensitivity analysis consider uncertainties in the initial and boundary conditions for the temperatures. Considering the volume-averaged air temperature on each floor, the predictions and measurements agree well with discrepancies less than 0.3 °C. When considering the temperature averaged over smaller zones on each floor, two trends can be observed. First, in zones not adjacent to windows, the discrepancies between the CFD and measurements can be explained by uncertainty in the boundary conditions and the measurements. Second, in zones adjacent to windows, higher discrepancies are observed due to oscillations in the inflow jets just downstream of the windows, and due to geometrical simplifications in the CFD model. The sensitivity analysis demonstrates that the boundary conditions for the thermal mass surface temperature and the outdoor temperature have a dominant effect on the indoor air temperature predictions, with their relative importance varying as function of proximity to the windows.

preprint2022arXiv

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

Compositing-aware object search aims to find the most compatible objects for compositing given a background image and a query bounding box. Previous works focus on learning compatibility between the foreground object and background, but fail to learn other important factors from large-scale data, i.e. geometry and lighting. To move a step further, this paper proposes GALA (Geometry-and-Lighting-Aware), a generic foreground object search method with discriminative modeling on geometry and lighting compatibility for open-world image compositing. Remarkably, it achieves state-of-the-art results on the CAIS dataset and generalizes well on large-scale open-world datasets, i.e. Pixabay and Open Images. In addition, our method can effectively handle non-box scenarios, where users only provide background images without any input bounding box. A web demo (see supplementary materials) is built to showcase applications of the proposed method for compositing-aware search and automatic location/scale prediction for the foreground object.

preprint2022arXiv

GAMa: Cross-view Video Geo-localization

The existing work in cross-view geo-localization is based on images where a ground panorama is matched to an aerial image. In this work, we focus on ground videos instead of images which provides additional contextual cues which are important for this task. There are no existing datasets for this problem, therefore we propose GAMa dataset, a large-scale dataset with ground videos and corresponding aerial images. We also propose a novel approach to solve this problem. At clip-level, a short video clip is matched with corresponding aerial image and is later used to get video-level geo-localization of a long video. Moreover, we propose a hierarchical approach to further improve the clip-level geolocalization. It is a challenging dataset, unaligned and limited field of view, and our proposed method achieves a Top-1 recall rate of 19.4% and 45.1% @1.0mile. Code and dataset are available at following link: https://github.com/svyas23/GAMa.

preprint2022arXiv

Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior

Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem which often requires prior assumptions on the solution space. In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model. Particularly, the proposed method leverages a variational autoencoder-based generative model to learn a manifold for biomechanically plausible deformations. The motion tracking then can be performed via traversing the learnt manifold to search for the optimal transformations while considering the sequence information. The proposed method is validated on three public cardiac cine MRI datasets with comprehensive evaluations. The results demonstrate that the proposed method can outperform other approaches, yielding higher motion tracking accuracy with reasonable volume preservation and better generalizability to varying data distributions. It also enables better estimates of myocardial strains, which indicates the potential of the method in characterizing spatiotemporal signatures for understanding cardiovascular diseases.

preprint2022arXiv

Geometric Transformers for Protein Interface Contact Prediction

Computational methods for predicting the interface contacts between proteins come highly sought after for drug discovery as they can significantly advance the accuracy of alternative approaches, such as protein-protein docking, protein function analysis tools, and other computational methods for protein bioinformatics. In this work, we present the Geometric Transformer, a novel geometry-evolving graph transformer for rotation and translation-invariant protein interface contact prediction, packaged within DeepInteract, an end-to-end prediction pipeline. DeepInteract predicts partner-specific protein interface contacts (i.e., inter-protein residue-residue contacts) given the 3D tertiary structures of two proteins as input. In rigorous benchmarks, DeepInteract, on challenging protein complex targets from the 13th and 14th CASP-CAPRI experiments as well as Docking Benchmark 5, achieves 14% and 1.1% top L/5 precision (L: length of a protein unit in a complex), respectively. In doing so, DeepInteract, with the Geometric Transformer as its graph-based backbone, outperforms existing methods for interface contact prediction in addition to other graph-based neural network backbones compatible with DeepInteract, thereby validating the effectiveness of the Geometric Transformer for learning rich relational-geometric features for downstream tasks on 3D protein structures.

preprint2022arXiv

Improved post-hoc probability calibration for out-of-domain MRI segmentation

Probability calibration for deep models is highly desirable in safety-critical applications such as medical imaging. It makes output probabilities of deep networks interpretable, by aligning prediction probability with the actual accuracy in test data. In image segmentation, well-calibrated probabilities allow radiologists to identify regions where model-predicted segmentations are unreliable. These unreliable predictions often occur to out-of-domain (OOD) images that are caused by imaging artifacts or unseen imaging protocols. Unfortunately, most previous calibration methods for image segmentation perform sub-optimally on OOD images. To reduce the calibration error when confronted with OOD images, we propose a novel post-hoc calibration model. Our model leverages the pixel susceptibility against perturbations at the local level, and the shape prior information at the global level. The model is tested on cardiac MRI segmentation datasets that contain unseen imaging artifacts and images from an unseen imaging protocol. We demonstrate reduced calibration errors compared with the state-of-the-art calibration algorithm.

preprint2022arXiv

Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning

Automated Audio captioning (AAC) is a cross-modal task that generates natural language to describe the content of input audio. Most prior works usually extract single-modality acoustic features and are therefore sub-optimal for the cross-modal decoding task. In this work, we propose a novel AAC system called CLIP-AAC to learn interactive cross-modality representation with both acoustic and textual information. Specifically, the proposed CLIP-AAC introduces an audio-head and a text-head in the pre-trained encoder to extract audio-text information. Furthermore, we also apply contrastive learning to narrow the domain difference by learning the correspondence between the audio signal and its paired captions. Experimental results show that the proposed CLIP-AAC approach surpasses the best baseline by a significant margin on the Clotho dataset in terms of NLP evaluation metrics. The ablation study indicates that both the pre-trained model and contrastive learning contribute to the performance gain of the AAC model.

preprint2022arXiv

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

Speech enhancement (SE) aims to suppress the additive noise from a noisy speech signal to improve the speech's perceptual quality and intelligibility. However, the over-suppression phenomenon in the enhanced speech might degrade the performance of downstream automatic speech recognition (ASR) task due to the missing latent information. To alleviate such problem, we propose an interactive feature fusion network (IFF-Net) for noise-robust speech recognition to learn complementary information from the enhanced feature and original noisy feature. Experimental results show that the proposed method achieves absolute word error rate (WER) reduction of 4.1% over the best baseline on RATS Channel-A corpus. Our further analysis indicates that the proposed IFF-Net can complement some missing information in the over-suppressed enhanced feature.

preprint2022arXiv

Joint Precoding and Phase Shift Design in Reconfigurable Intelligent Surfaces-Assisted Secret Key Generation

Key generation is a promising technique to establish symmetric keys between resource-constrained legitimate users. However, key generation suffers from low secret key rate (SKR) in harsh environments where channel randomness is limited. To address the problem, reconfigurable intelligent surfaces (RISs) are introduced to reshape the channels by controlling massive reflecting elements, which can provide more channel diversity. In this paper, we design a channel probing protocol to fully extract the randomness from the cascaded channel, i.e., the channel through reflecting elements. We derive the analytical expressions of SKR and design a water-filling algorithm based on the Karush-Kuhn-Tucker (KKT) conditions to find the upper bound. To find the optimal precoding and phase shift matrices, we propose an algorithm based on the Grassmann manifold optimization methods. The system is evaluated in terms of SKR, bit disagreement rate (BDR) and randomness. Simulation results show that our protocols significantly improve the SKR as compared to existing protocol.

preprint2022arXiv

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model. Instead, we consider rethinking solutions to data heterogeneity in FL with a focus on local learning generality rather than proximal restriction. To this end, we first present a systematic study informed by second-order indicators to better understand algorithm effectiveness in FL. Interestingly, we find that standard regularization methods are surprisingly strong performers in mitigating data heterogeneity effects. Based on our findings, we further propose a simple and effective method, FedAlign, to overcome data heterogeneity and the pitfalls of previous methods. FedAlign achieves competitive accuracy with state-of-the-art FL methods across a variety of settings while minimizing computation and memory overhead. Code is available at https://github.com/mmendiet/FedAlign

preprint2022arXiv

M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.

preprint2022arXiv

Magic ELF: Image Deraining Meets Association Learning and Transformer

Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmonize these two architectures to satisfy image deraining. This paper aims to unify these two architectures to take advantage of their learning merits for image deraining. In particular, the local connectivity and translation equivariance of CNN and the global aggregation ability of self-attention (SA) in Transformer are fully exploited for specific local context and global structure representations. Based on the observation that rain distribution reveals the degradation location and degree, we introduce degradation prior to help background recovery and accordingly present the association refinement deraining scheme. A novel multi-input attention module (MAM) is proposed to associate rain perturbation removal and background recovery. Moreover, we equip our model with effective depth-wise separable convolutions to learn the specific feature representations and trade off computational complexity. Extensive experiments show that our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average, but only accounts for 11.7\% and 42.1\% of its computational cost and parameters. The source code is available at https://github.com/kuijiang94/Magic-ELF.

preprint2022arXiv

Masked Spatial-Spectral Autoencoders Are Excellent Hyperspectral Defenders

Deep learning methodology contributes a lot to the development of hyperspectral image (HSI) analysis community. However, it also makes HSI analysis systems vulnerable to adversarial attacks. To this end, we propose a masked spatial-spectral autoencoder (MSSA) in this paper under self-supervised learning theory, for enhancing the robustness of HSI analysis systems. First, a masked sequence attention learning module is conducted to promote the inherent robustness of HSI analysis systems along spectral channel. Then, we develop a graph convolutional network with learnable graph structure to establish global pixel-wise combinations.In this way, the attack effect would be dispersed by all the related pixels among each combination, and a better defense performance is achievable in spatial aspect.Finally, to improve the defense transferability and address the problem of limited labelled samples, MSSA employs spectra reconstruction as a pretext task and fits the datasets in a self-supervised manner.Comprehensive experiments over three benchmarks verify the effectiveness of MSSA in comparison with the state-of-the-art hyperspectral classification methods and representative adversarial defense strategies.

preprint2022arXiv

MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation

Convolutional neural networks (CNNs) have achieved remarkable segmentation accuracy on benchmark datasets where training and test sets are from the same domain, yet their performance can degrade significantly on unseen domains, which hinders the deployment of CNNs in many clinical scenarios. Most existing works improve model out-of-domain (OOD) robustness by collecting multi-domain datasets for training, which is expensive and may not always be feasible due to privacy and logistical issues. In this work, we focus on improving model robustness using a single-domain dataset only. We propose a novel data augmentation framework called MaxStyle, which maximizes the effectiveness of style augmentation for model OOD performance. It attaches an auxiliary style-augmented image decoder to a segmentation network for robust feature learning and data augmentation. Importantly, MaxStyle augments data with improved image style diversity and hardness, by expanding the style space with noise and searching for the worst-case style composition of latent features via adversarial training. With extensive experiments on multiple public cardiac and prostate MR datasets, we demonstrate that MaxStyle leads to significantly improved out-of-distribution robustness against unseen corruptions as well as common distribution shifts across multiple, different, unseen sites and unknown image sequences under both low- and high-training data settings. The code can be found at https://github.com/cherise215/MaxStyle.

preprint2022arXiv

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

For 3D medical image (e.g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly. Previous research on volumetric medical image segmentation in a slice-by-slice manner conventionally use the identical 2D deep neural network to segment all the slices of the same case, ignoring the data heterogeneity among image slices. In this paper, we focus on multi-modal 3D MRI brain tumor segmentation and propose a dynamic architecture network named Med-DANet based on adaptive model selection to achieve effective accuracy and efficiency trade-off. For each slice of the input 3D MRI volume, our proposed method learns a slice-specific decision by the Decision Network to dynamically select a suitable model from the predefined Model Bank for the subsequent 2D segmentation task. Extensive experimental results on both BraTS 2019 and 2020 datasets show that our proposed method achieves comparable or better results than previous state-of-the-art methods for 3D MRI brain tumor segmentation with much less model complexity. Compared with the state-of-the-art 3D method TransBTS, the proposed framework improves the model efficiency by up to 3.5x without sacrificing the accuracy. Our code will be publicly available soon.

preprint2022arXiv

Multimodal Transformer for Nursing Activity Recognition

In an aging population, elderly patient safety is a primary concern at hospitals and nursing homes, which demands for increased nurse care. By performing nurse activity recognition, we can not only make sure that all patients get an equal desired care, but it can also free nurses from manual documentation of activities they perform, leading to a fair and safe place of care for the elderly. In this work, we present a multimodal transformer-based network, which extracts features from skeletal joints and acceleration data, and fuses them to perform nurse activity recognition. Our method achieves state-of-the-art performance of 81.8% accuracy on the benchmark dataset available for nurse activity recognition from the Nurse Care Activity Recognition Challenge. We perform ablation studies to show that our fusion model is better than single modality transformer variants (using only acceleration or skeleton joints data). Our solution also outperforms state-of-the-art ST-GCN, GRU and other classical hand-crafted-feature-based classifier solutions by a margin of 1.6%, on the NCRC dataset. Code is available at \url{https://github.com/Momilijaz96/MMT_for_NCRC}.

preprint2022arXiv

Mutual Inclination of Ultra-Short-Period Planets with Time Varying Stellar J2-moment

Systems with ultra-short-period planets (USPs) tend to possess larger mutual inclinations compared to those with planets located farther from their host stars. This could be explained due to precession caused by stellar oblateness at early times when the host star was rapidly spinning. However, stellar oblateness reduces over time due to the decrease in the stellar rotation rate, and this may further shape the planetary mutual inclinations. In this work, we investigate in detail how the final mutual inclination varies under the effect of a decreasing $J_2$. We find that different initial parameters (e.g., the magnitude of $J_2$ and planetary inclinations) will contribute to different final mutual inclinations, providing a constraint on the formation mechanisms of USPs. In general, if the inner planets start in the same plane as the stellar equator (or co-planar while misaligned with the stellar spin-axis), the mutual inclination decreases (or increases then decreases) over time due to the decay of the $J_2$ moment. This is because the inner orbit typically possesses less orbital angular momentum than the outer ones. However, if the outer planet is initially aligned with the stellar spin while the inner one is misaligned, the mutual inclination nearly stays the same. Overall, our results suggest that either the USP planets formed early and acquired significant inclinations (e.g., $\gtrsim30^\circ$ with its companion or $\gtrsim10^\circ$ with its host star spin-axis for Kepler-653c) or they formed late ($\gtrsim$Gyr) when their host stars rotate slower.

preprint2022arXiv

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

preprint2022arXiv

Nonnegative Tensor Completion via Integer Optimization

Unlike matrix completion, tensor completion does not have an algorithm that is known to achieve the information-theoretic sample complexity rate. This paper develops a new algorithm for the special case of completion for nonnegative tensors. We prove that our algorithm converges in a linear (in numerical tolerance) number of oracle steps, while achieving the information-theoretic rate. Our approach is to define a new norm for nonnegative tensors using the gauge of a particular 0-1 polytope; integer linear programming can, in turn, be used to solve linear separation problems over this polytope. We combine this insight with a variant of the Frank-Wolfe algorithm to construct our numerical algorithm, and we demonstrate its effectiveness and scalability through computational experiments using a laptop on tensors with up to one-hundred million entries.

preprint2022arXiv

Nucleon axial-vector and pseudoscalar form factors, and PCAC relations

We use a continuum quark+diquark approach to the nucleon bound-state problem in relativistic quantum field theory to deliver parameter-free predictions for the nucleon axial and induced pseudoscalar form factors, $G_A$ and $G_P$, and unify them with the pseudoscalar form factor $G_5$ or, equivalently, the pion-nucleon form factor $G_{πNN}$. We explain how partial conservation of the axial-vector current and the associated Goldberger-Treiman relation are satisfied once all necessary couplings of the external current to the building blocks of the nucleon are constructed consistently; in particular, we fully resolve the seagull couplings to the diquark-quark vertices associated with the axial-vector and pseudoscalar currents. Among the results we describe, the following are worth highlighting. A dipole form factor defined by an axial charge $g_A=G_A(0)=1.25(3)$ and a mass-scale $M_A = 1.23(3) m_N$, where $m_N$ is the nucleon mass, can accurately describe the pointwise behaviour of $G_A$. Concerning $G_P$, we obtain the pseudoscalar charge $g_p^\ast = 8.80(23)$, and find that the pion pole dominance approach delivers a reliable estimate of the directly computed result. Our computed value of the pion-nucleon coupling constant, $g_{πNN}/m_N =14.02(33)/{\rm GeV}$ is consistent with recent precision determinations.

preprint2022arXiv

Primal-dual Estimator Learning: an Offline Constrained Moving Horizon Estimation Method with Feasibility and Near-optimality Guarantees

This paper proposes a primal-dual framework to learn a stable estimator for linear constrained estimation problems leveraging the moving horizon approach. To avoid the online computational burden in most existing methods, we learn a parameterized function offline to approximate the primal estimate. Meanwhile, a dual estimator is trained to check the suboptimality of the primal estimator during execution time. Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality. This in turn allows us to bound the probability of the learned estimator being infeasible or suboptimal. Furthermore, we analyze the stability of the resulting estimator with a bounded error in the minimization of the cost function. Since our algorithm does not require the solution of an optimization problem during runtime, state estimates can be generated online almost instantly. Simulation results are presented to show the accuracy and time efficiency of the proposed framework compared to online optimization of moving horizon estimation and Kalman filter. To the best of our knowledge, this is the first learning-based state estimator with feasibility and near-optimality guarantees for linear constrained systems.

preprint2022arXiv

Privacy and Robustness in Federated Learning: Attacks and Defenses

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.

preprint2022arXiv

Real-space Observation of Incommensurate Spin Density Wave and Coexisting Charge Density Wave on Cr(001) surface

In itinerant magnetic systems, a spin density wave (SDW) state can be induced by Fermi surface nesting and electron-electron interaction. It may intertwine with other orders such as charge density wave (CDW), while their relation is still yet to be understood. Here via spin-polarized scanning tunneling microscopy, we directly observed long-range spin modulation on Cr(001) surface, which corresponds to the well-known incommensurate SDW of bulk Cr. It displays 6.0 nm in-plane period and anti-phase behavior between adjacent (001) planes. Meanwhile, we simultaneously observed the coexisting CDW with half the period of SDW. Such SDW/CDW have highly correlated domain structures and are in-phase. Surprisingly, the CDW displays a contrast inversion around a density-of-states dip at -22 meV, indicating an anomalous CDW gap opened below EF. These observations support that the CDW is a secondary order driven by SDW. Our work is not only a real-space characterization of incommensurate SDW, but also provides insights on how SDW and CDW coexist.

preprint2022arXiv

Resilient Distribution System Restoration with Communication Recovery by Drone Small Cells

Distribution system (DS) restoration after natural disasters often faces the challenge of communication failures to feeder automation (FA) facilities, resulting in prolonged load pick-up process. This letter discusses the utilization of drone small cells for wireless communication recovery of FA, and proposes an integrated DS restoration strategy with communication recovery. Demonstrative case studies are conducted to validate the proposed model, and its advantages are illustrated by comparing to benchmark strategies.

preprint2022arXiv

Rethinking Reinforcement Learning based Logic Synthesis

Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process. However, through extensive experiments, we find out that the learned policy makes decisions independent from the circuit features (i.e., states) and yields an operator sequence that is permutation invariant to some extent in terms of operators. Based on these findings, we develop a new RL-based method that can automatically recognize critical operators and generate common operator sequences generalizable to unseen circuits. Our algorithm is verified on both the EPFL benchmark, a private dataset and a circuit at industrial scale. Experimental results demonstrate that it achieves a good balance among delay, area and runtime, and is practical for industrial usage.

preprint2022arXiv

RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation

Source code authorship attribution is an important problem often encountered in applications such as software forensics, bug fixing, and software quality analysis. Recent studies show that current source code authorship attribution methods can be compromised by attackers exploiting adversarial examples and coding style manipulation. This calls for robust solutions to the problem of code authorship attribution. In this paper, we initiate the study on making Deep Learning (DL)-based code authorship attribution robust. We propose an innovative framework called Robust coding style Patterns Generation (RoPGen), which essentially learns authors' unique coding style patterns that are hard for attackers to manipulate or imitate. The key idea is to combine data augmentation and gradient augmentation at the adversarial training phase. This effectively increases the diversity of training examples, generates meaningful perturbations to gradients of deep neural networks, and learns diversified representations of coding styles. We evaluate the effectiveness of RoPGen using four datasets of programs written in C, C++, and Java. Experimental results show that RoPGen can significantly improve the robustness of DL-based code authorship attribution, by respectively reducing 22.8% and 41.0% of the success rate of targeted and untargeted attacks on average.

preprint2022arXiv

SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection

Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects. To tackle this issue, we propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA). Technically, we first add a binary segmentation module as the side output to help identify foreground points. Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection. Additionally, it is an easy-to-plug-in module and able to boost various point-based detectors, including single-stage and two-stage ones. Extensive experiments on the popular KITTI and nuScenes datasets validate the superiority of SASA, lifting point-based detection models to reach comparable performance to state-of-the-art voxel-based methods.

preprint2022arXiv

Self-critical Sequence Training for Automatic Speech Recognition

Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used cross-entropy criterion aims to maximize log-likelihood of the training data, while the performance is evaluated by word error rate (WER), not log-likelihood; 2) The teacher-forcing method leads to the dependence on ground truth during training, which means that model has never been exposed to its own prediction before testing. In this paper, we propose an optimization method called self-critical sequence training (SCST) to make the training procedure much closer to the testing phase. As a reinforcement learning (RL) based method, SCST utilizes a customized reward function to associate the training criterion and WER. Furthermore, it removes the reliance on teacher-forcing and harmonizes the model with respect to its inference procedure. We conducted experiments on both clean and noisy speech datasets, and the results show that the proposed SCST respectively achieves 8.7% and 7.8% relative improvements over the baseline in terms of WER.

preprint2022arXiv

SPAct: Self-supervised Privacy Preservation for Action Recognition

Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. However, annotating frames of video dataset for privacy labels is not feasible. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. For the first time, we present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels. Our training framework consists of three main components: anonymization function, self-supervised privacy removal branch, and action recognition branch. We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss. Employing existing protocols of known-action and privacy attributes, our framework achieves a competitive action-privacy trade-off to the existing state-of-the-art supervised methods. In addition, we introduce a new protocol to evaluate the generalization of learned the anonymization function to novel-action and privacy attributes and show that our self-supervised framework outperforms existing supervised methods. Code available at: https://github.com/DAVEISHAN/SPAct

preprint2022arXiv

Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information

Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. In this paper, we propose an end-to-end speech emotion recognition system using multi-level acoustic information with a newly designed co-attention module. We firstly extract multi-level acoustic information, including MFCC, spectrogram, and the embedded high-level acoustic information with CNN, BiLSTM and wav2vec2, respectively. Then these extracted features are treated as multimodal inputs and fused by the proposed co-attention mechanism. Experiments are carried on the IEMOCAP dataset, and our model achieves competitive performance with two different speaker-independent cross-validation strategies. Our code is available on GitHub.

preprint2022arXiv

Task-Adaptive Few-shot Node Classification

Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph Neural Networks (GNNs) have achieved significant improvements in node classification, their performance decreases substantially in such a few-shot scenario. The main reason can be attributed to the vast generalization gap between meta-training and meta-test due to the task variance caused by different node/class distributions in meta-tasks (i.e., node-level and class-level variance). Therefore, to effectively alleviate the impact of task variance, we propose a task-adaptive node classification framework under the few-shot learning setting. Specifically, we first accumulate meta-knowledge across classes with abundant labeled nodes. Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules. In particular, to accommodate the different node/class distributions among meta-tasks, we propose three essential modules to perform \emph{node-level}, \emph{class-level}, and \emph{task-level} adaptations in each meta-task, respectively. In this way, our framework can conduct adaptations to different meta-tasks and thus advance the model generalization performance on meta-test tasks. Extensive experiments on four prevalent node classification datasets demonstrate the superiority of our framework over the state-of-the-art baselines. Our code is provided at https://github.com/SongW-SW/TENT.

preprint2022arXiv

Towards a category-extended object detector with limited data

Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old classes and some new training data labeled with new classes are available in such scenarios. Based on the limited datasets, a unified detector that can handle all categories is strongly needed. We propose a practical scheme to achieve it in this work. A conflict-free loss is designed to avoid label ambiguity, leading to an acceptable detector in one training round. To further improve performance, we propose a retraining phase in which Monte Carlo Dropout is employed to calculate the localization confidence to mine more accurate bounding boxes, and an overlap-weighted method is proposed for making better use of pseudo annotations during retraining. Extensive experiments demonstrate the effectiveness of our method.

preprint2022arXiv

Towards Visualization of Time-Series Ecological Momentary Assessment (EMA) Data on Standalone Voice-First Virtual Assistants

Population aging is an increasingly important consideration for health care in the 21th century, and continuing to have access and interact with digital health information is a key challenge for aging populations. Voice-based Intelligent Virtual Assistants (IVAs) are promising to improve the Quality of Life (QoL) of older adults, and coupled with Ecological Momentary Assessments (EMA) they can be effective to collect important health information from older adults, especially when it comes to repeated time-based events. However, this same EMA data is hard to access for the older adult: although the newest IVAs are equipped with a display, the effectiveness of visualizing time-series based EMA data on standalone IVAs has not been explored. To investigate the potential opportunities for visualizing time-series based EMA data on standalone IVAs, we designed a prototype system, where older adults are able to query and examine the time-series EMA data on Amazon Echo Show - a widely used commercially available standalone screen-based IVA. We conducted a preliminary semi-structured interview with a geriatrician and an older adult, and identified three findings that should be carefully considered when designing such visualizations.

preprint2022arXiv

TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images

Transformer, benefiting from global (long-range) information modeling using self-attention mechanism, has been successful in natural language processing and computer vision recently. Convolutional Neural Networks, capable of capturing local features, are difficult to model explicit long-distance dependencies from global feature space. However, both local and global features are crucial for dense prediction tasks, especially for 3D medical image segmentation. In this paper, we present the further attempt to exploit Transformer in 3D CNN for 3D medical image volumetric segmentation and propose a novel network named TransBTSV2 based on the encoder-decoder structure. Different from TransBTS, the proposed TransBTSV2 is not limited to brain tumor segmentation (BTS) but focuses on general medical image segmentation, providing a stronger and more efficient 3D baseline for volumetric segmentation of medical images. As a hybrid CNN-Transformer architecture, TransBTSV2 can achieve accurate segmentation of medical images without any pre-training, possessing the strong inductive bias as CNNs and powerful global context modeling ability as Transformer. With the proposed insight to redesign the internal structure of Transformer block and the introduced Deformable Bottleneck Module to capture shape-aware local details, a highly efficient architecture is achieved with superior performance. Extensive experimental results on four medical image datasets (BraTS 2019, BraTS 2020, LiTS 2017 and KiTS 2019) demonstrate that TransBTSV2 achieves comparable or better results compared to the state-of-the-art methods for the segmentation of brain tumor, liver tumor as well as kidney tumor. Code will be publicly available at https://github.com/Wenxuan-1119/TransBTS.

preprint2022arXiv

TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization

The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.

preprint2022arXiv

Wave functions of $(I,J^P) = (\tfrac{1}{2},\tfrac{3}{2}^\mp)$ baryons

Using a Poincaré-covariant quark+diquark Faddeev equation, we provide structural information on the four lightest $(I,J^P)=(\tfrac{1}{2},\tfrac{3}{2}^\mp)$ baryon multiplets. These systems may contain five distinct types of diquarks; but in order to obtain reliable results, it is sufficient to retain only isoscalar-scalar and isovector-axialvector correlations, with the latter being especially important. Viewed with low resolution, the Faddeev equation description of these states bears some resemblance to the associated quark model pictures; namely, they form a set of states related via orbital angular momentum excitation: the negative parity states are primarily $\mathsf P$-wave in character, whereas the positive parity states are $\mathsf D$ wave. However, a closer look reveals far greater structural complexity than is typical of quark model descriptions, with $\mathsf P$, $\mathsf D$, $\mathsf S$, $\mathsf F$ waves and interferences between them all playing a large role in forming observables. Large momentum transfer resonance electroexcitation measurements can be used to test these predictions and may thereby provide insights into the nature of emergent hadron mass.

preprint2021arXiv

A Catalog of High-Velocity CIV Mini-BALs in the VLT-UVES and Keck-HIRES Archives

We present a catalog of high-velocity CIV $λ$ 1548,1551 mini-Broad Absorption Lines (mini-BALs) in the archives of the VLT-UVES and Keck-HIRES spectrographs. We identify high-velocity CIV mini-BALs based on smooth rounded BAL-like profiles with velocity blueshifts $<$ $-$4000 km/s and widths in the range 70 $\lesssim$ FWHM(1548) $\lesssim$ 2000 km/s (for $λ$1548 alone). We find 105 mini-BALs in 44 quasars from a total sample of 638 quasars. The fraction of quasars with at least one mini-BAL meeting our criteria is roughly $\sim9$% after correcting for incomplete velocity coverage. However, the numbers of systems rise sharply at lower velocities and narrower FWHMs, suggesting that many outflow lines are missed by our study. All of the systems are highly ionized based on the strong presence of NV and OVI and/or the absence of SiII and CII when within the wavelength coverage. Two of the mini-BAL systems in our catalog, plus three others at smaller velocity shifts, have PV $λ$1118,1128 absorption indicating highly saturated CIV absorption and total hydrogen column densities $\gtrsim 10^{22}$ cm$^{-3}$. Most of the mini-BALs are confirmed to have optical depths $\gtrsim$1 with partial covering of the quasar continuum source. The covering fractions are as small as 0.06 in CIV and 0.03 in SiIV , corresponding to outflow absorbing structures $<0.002$ pc across. When multiple lines are measured, the lines of less abundant ions tend to have narrower profiles and smaller covering fractions indicative of inhomogeneous absorbers where higher column densities occur in smaller clumps. This picture might extend to BAL outflows if the broader and generally deeper BALs form in either the largest clumps or collections of many mini-BAL-like clumps that blend together in observed quasar spectra.

preprint2021arXiv

A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images

Malaria microscopy, microscopic examination of stained blood slides to detect parasite Plasmodium, is considered to be a gold-standard for detecting life-threatening disease malaria. Detecting the plasmodium parasite requires a skilled examiner and may take up to 10 to 15 minutes to completely go through the whole slide. Due to a lack of skilled medical professionals in the underdeveloped or resource deficient regions, many cases go misdiagnosed; resulting in unavoidable complications and/or undue medication. We propose to complement the medical professionals by creating a deep learning-based method to automatically detect (localize) the plasmodium parasites in the photograph of stained film. To handle the unbalanced nature of the dataset, we adopt a two-stage approach. Where the first stage is trained to detect blood cells and classify them into just healthy or infected. The second stage is trained to classify each detected cell further into the life-cycle stage. To facilitate the research in machine learning-based malaria microscopy, we introduce a new large scale microscopic image malaria dataset. Thirty-eight thousand cells are tagged from the 345 microscopic images of different Giemsa-stained slides of blood samples. Extensive experimentation is performed using different CNN backbones including VGG, DenseNet, and ResNet on this dataset. Our experiments and analysis reveal that the two-stage approach works better than the one-stage approach for malaria detection. To ensure the usability of our approach, we have also developed a mobile app that will be used by local hospitals for investigation and educational purposes. The dataset, its annotations, and implementation codes will be released upon publication of the paper.

preprint2021arXiv

A Transferable Anti-Forensic Attack on Forensic CNNs Using A Generative Adversarial Network

With the development of deep learning, convolutional neural networks (CNNs) have become widely used in multimedia forensics for tasks such as detecting and identifying image forgeries. Meanwhile, anti-forensic attacks have been developed to fool these CNN-based forensic algorithms. Previous anti-forensic attacks often were designed to remove forgery traces left by a single manipulation operation as opposed to a set of manipulations. Additionally, recent research has shown that existing anti-forensic attacks against forensic CNNs have poor transferability, i.e. they are unable to fool other forensic CNNs that were not explicitly used during training. In this paper, we propose a new anti-forensic attack framework designed to remove forensic traces left by a variety of manipulation operations. This attack is transferable, i.e. it can be used to attack forensic CNNs are unknown to the attacker, and it introduces only minimal distortions that are imperceptible to human eyes. Our proposed attack utilizes a generative adversarial network (GAN) to build a generator that can attack color images of any size. We achieve attack transferability through the use of a new training strategy and loss function. We conduct extensive experiment to demonstrate that our attack can fool many state-of-art forensic CNNs with varying levels of knowledge available to the attacker.

preprint2021arXiv

Addressing Action Oscillations through Learning Policy Inertia

Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective in a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in discrete action setting, which means that agents select different actions within consecutive steps even though states only slightly differ. This issue is often neglected since the policy is usually evaluated by its cumulative rewards only. Action oscillation strongly affects the user experience and can even cause serious potential security menace especially in real-world domains with the main concern of safety, such as autonomous driving. To this end, we introduce Policy Inertia Controller (PIC) which serves as a generic plug-in framework to off-the-shelf DRL algorithms, to enables adaptive trade-off between the optimality and smoothness of the learned policy in a formal way. We propose Nested Policy Iteration as a general training algorithm for PIC-augmented policy which ensures monotonically non-decreasing updates under some mild conditions. Further, we derive a practical DRL algorithm, namely Nested Soft Actor-Critic. Experiments on a collection of autonomous driving tasks and several Atari games suggest that our approach demonstrates substantial oscillation reduction in comparison to a range of commonly adopted baselines with almost no performance degradation.

preprint2021arXiv

BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images

Fast and effective responses are required when a natural disaster (e.g., earthquake, hurricane, etc.) strikes. Building damage assessment from satellite imagery is critical before relief effort is deployed. With a pair of pre- and post-disaster satellite images, building damage assessment aims at predicting the extent of damage to buildings. With the powerful ability of feature representation, deep neural networks have been successfully applied to building damage assessment. Most existing works simply concatenate pre- and post-disaster images as input of a deep neural network without considering their correlations. In this paper, we propose a novel two-stage convolutional neural network for Building Damage Assessment, called BDANet. In the first stage, a U-Net is used to extract the locations of buildings. Then the network weights from the first stage are shared in the second stage for building damage assessment. In the second stage, a two-branch multi-scale U-Net is employed as backbone, where pre- and post-disaster images are fed into the network separately. A cross-directional attention module is proposed to explore the correlations between pre- and post-disaster images. Moreover, CutMix data augmentation is exploited to tackle the challenge of difficult classes. The proposed method achieves state-of-the-art performance on a large-scale dataset -- xBD. The code is available at https://github.com/ShaneShen/BDANet-Building-Damage-Assessment.

preprint2021arXiv

DeepGOMIMO: Deep Learning-Aided Generalized Optical MIMO with CSI-Free Blind Detection

Generalized optical multiple-input multiple-output (GOMIMO) techniques have been recently shown to be promising for high-speed optical wireless communication (OWC) systems. In this paper, we propose a novel deep learning-aided GOMIMO (DeepGOMIMO) framework for GOMIMO systems, where channel state information (CSI)-free blind detection can be enabled by employing a specially designed deep neural network (DNN)-based MIMO detector. The CSI-free blind DNN detector mainly consists of two modules: one is the pre-processing module which is designed to address both the path loss and channel crosstalk issues caused by MIMO transmission, and the other is the feed-forward DNN module which is used for joint detection of spatial and constellation information by learning the statistics of both the input signal and the additive noise. Our simulation results clearly verify that, in a typical indoor 4 $\times$ 4 MIMO-OWC system using both generalized optical spatial modulation (GOSM) and generalized optical spatial multiplexing (GOSMP) with unipolar non-zero 4-ary pulse amplitude modulation (4-PAM) modulation, the proposed CSI-free blind DNN detector achieves near the same bit error rate (BER) performance as the optimal joint maximum-likelihood (ML) detector, but with much reduced computational complexity. Moreover, since the CSI-free blind DNN detector does not require instantaneous channel estimation to obtain accurate CSI, it enjoys the unique advantages of improved achievable data rate and reduced communication time delay in comparison to the CSI-based zero-forcing DNN (ZF-DNN) detector.

preprint2021arXiv

Direct observation of layer-stacking and oriented wrinkles in multilayer hexagonal boron nitride

Hexagonal boron nitride (h-BN) has long been recognized as an ideal substrate for electronic devices due to its dangling-bond-free surface, insulating nature and thermal/chemical stability. Therefore, to analyse the lattice structure and orientation of h-BN crystals becomes important. Here, the stacking order and wrinkles of h-BN are investigated by transmission electron microscopy (TEM). It is experimentally confirmed that the layers in the h-BN flakes are arranged in the AA' stacking. The wrinkles in a form of threefold network throughout the h-BN crystal are oriented along the armchair direction, and their formation mechanism was further explored by molecular dynamics simulations. Our findings provide a deep insight about the microstructure of h-BN and shed light on the structural design/electronic modulations of two-dimensional crystals.

preprint2021arXiv

Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other forms of constraints can be incorporated into the attention framework for learning long-range dependencies for the task of pose estimation. The contribution of this paper is to provide a systematic approach for designing and training of attention-based models for the end-to-end pose estimation, with the flexibility and scalability of arbitrary video sequences as input. We achieve this by adapting temporal receptive field via a multi-scale structure of dilated convolutions. Besides, the proposed architecture can be easily adapted to a causal model enabling real-time performance. Any off-the-shelf 2D pose estimation systems, e.g. Mocap libraries, can be easily integrated in an ad-hoc fashion. Our method achieves the state-of-the-art performance and outperforms existing methods by reducing the mean per joint position error to 33.4 mm on Human3.6M dataset.

preprint2021arXiv

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

Value function is the central notion of Reinforcement Learning (RL). Value estimation, especially with function approximation, can be challenging since it involves the stochasticity of environmental dynamics and reward signals that can be sparse and delayed in some cases. A typical model-free RL algorithm usually estimates the values of a policy by Temporal Difference (TD) or Monte Carlo (MC) algorithms directly from rewards, without explicitly taking dynamics into consideration. In this paper, we propose Value Decomposition with Future Prediction (VDFP), providing an explicit two-step understanding of the value estimation process: 1) first foresee the latent future, 2) and then evaluate it. We analytically decompose the value function into a latent future dynamics part and a policy-independent trajectory return part, inducing a way to model latent dynamics and returns separately in value estimation. Further, we derive a practical deep RL algorithm, consisting of a convolutional model to learn compact trajectory representation from past experiences, a conditional variational auto-encoder to predict the latent future dynamics and a convex return model that evaluates trajectory representation. In experiments, we empirically demonstrate the effectiveness of our approach for both off-policy and on-policy RL in several OpenAI Gym continuous control tasks as well as a few challenging variants with delayed reward.

preprint2021arXiv

Guided Interpolation for Adversarial Training

To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data. However, as the training progresses, the training data becomes less and less attackable, undermining the robustness enhancement. A straightforward remedy is to incorporate more training data, but sometimes incurring an unaffordable cost. In this paper, to mitigate this issue, we propose the guided interpolation framework (GIF): in each epoch, the GIF employs the previous epoch's meta information to guide the data's interpolation. Compared with the vanilla mixup, the GIF can provide a higher ratio of attackable data, which is beneficial to the robustness enhancement; it meanwhile mitigates the model's linear behavior between classes, where the linear behavior is favorable to generalization but not to the robustness. As a result, the GIF encourages the model to predict invariantly in the cluster of each class. Experiments demonstrate that the GIF can indeed enhance adversarial robustness on various adversarial training methods and various datasets.

preprint2021arXiv

Moiré Imaging in Twisted Bilayer Graphene Aligned on Hexagonal Boron Nitride

Moiré superlattices (MSL) formed in angle-aligned bilayers of van der Waals materials have become a promising platform to realize novel two-dimensional electronic states. Angle-aligned trilayer structures can form two sets of MSLs which could potentially interfere with each other. In this work, we directly image the moiré patterns in both monolayer graphene aligned on hBN and twisted bilayer graphene aligned on hBN, using combined scanning microwave impedance microscopy and conductive atomic force microscopy. Correlation of the two techniques reveals the contrast mechanism for the achieved ultrahigh spatial resolution (<2 nm). We observe two sets of MSLs with different periodicities in the trilayer stack. The smaller MSL breaks the 6-fold rotational symmetry and exhibits abrupt discontinuities at the boundaries of the larger MSL. Using a rigid atomic-stacking model, we demonstrate that the hBN layer considerably modifies the MSL of twisted bilayer graphene. We further analyze its effect on the reciprocal space spectrum of the dual-moiré system.

preprint2021arXiv

MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations

Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change with different scenarios, and repeatedly training networks for each required budget would be incredibly expensive. Therefore, in this work, we propose a general method called MutualNet to train a single network that can run at a diverse set of resource constraints. Our method trains a cohort of model configurations with various network widths and input resolutions. This mutual learning scheme not only allows the model to run at different width-resolution configurations but also transfers the unique knowledge among these configurations, helping the model to learn stronger representations overall. MutualNet is a general training methodology that can be applied to various network structures (e.g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e.g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets. Since we only train the model once, it also greatly reduces the training cost compared to independently training several models. Surprisingly, MutualNet can also be used to significantly boost the performance of a single network, if dynamic resource constraint is not a concern. In summary, MutualNet is a unified method for both static and adaptive, 2D and 3D networks. Codes and pre-trained models are available at \url{https://github.com/taoyang1122/MutualNet}.

preprint2021arXiv

REMIX: Efficient Range Query for LSM-trees

LSM-tree based key-value (KV) stores organize data in a multi-level structure for high-speed writes. Range queries on traditional LSM-trees must seek and sort-merge data from multiple table files on the fly, which is expensive and often leads to mediocre read performance. To improve range query efficiency on LSM-trees, we introduce a space-efficient KV index data structure, named REMIX, that records a globally sorted view of KV data spanning multiple table files. A range query on multiple REMIX-indexed data files can quickly locate the target key using a binary search, and retrieve subsequent keys in sorted order without key comparisons. We build RemixDB, an LSM-tree based KV-store that adopts a write-efficient compaction strategy and employs REMIXes for fast point and range queries. Experimental results show that REMIXes can substantially improve range query performance in a write-optimized LSM-tree based KV-store.

preprint2021arXiv

Robust Trajectory-Constrained Frequency Control for Microgrids Considering Model Linearization Error

The capability to switch between grid-connected and islanded modes has promoted adoption of microgrid technology for powering remote locations. Stabilizing frequency during the islanding event, however, is a challenging control task, particularly under high penetration of converter-interfaced sources. In this paper, a numerical optimal control (NOC)-based control synthesis methodology is proposed for preparedness of microgrid islanding that ensure guaranteed performance. The key feature of the proposed paradigm is near real-time centralized scheduling for real-time decentralized executing. For tractable computation, linearized models are used in the problem formulation. To accommodate the linearization errors, interval analysis is employed to compute linearization-induced uncertainty as numerical intervals so that the NOC problem can be formulated into a robust mixed-integer linear program. The proposed control is verified on the full nonlinear model in Simulink. The simulation results shown effectiveness of the proposed control paradigm and the necessity of considering linearization-induced uncertainty.

preprint2021arXiv

Structural and dynamic disorder, not ionic trapping, controls charge transport in highly doped conducting polymers

Doped organic semiconductors are critical to emerging device applications, including thermoelectrics, bioelectronics, and neuromorphic computing devices. It is commonly assumed that low conductivities in these materials result primarily from charge trapping by the Coulomb potentials of the dopant counter-ions. Here, we present a combined experimental and theoretical study rebutting this belief. Using a newly developed doping technique, we find the conductivity of several classes of high-mobility conjugated polymers to be strongly correlated with paracrystalline disorder but poorly correlated with ionic size, suggesting that Coulomb traps do not limit transport. A general model for interacting electrons in highly doped polymers is proposed and carefully parameterized against atomistic calculations, enabling the calculation of electrical conductivity within the framework of transient localisation theory. Theoretical calculations are in excellent agreement with experimental data, providing insights into the disordered-limited nature of charge transport and suggesting new strategies to further improve conductivities.

preprint2020arXiv

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging

Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation of LGE-MRIs is challenging due to its attenuated contrast. Since most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double, sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved far superior results than traditional methods and pipelines containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for cardiac LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field.

preprint2020arXiv

Action recognition in real-world videos

The goal of human action recognition is to temporally or spatially localize the human action of interest in video sequences. Temporal localization (i.e. indicating the start and end frames of the action in a video) is referred to as frame-level detection. Spatial localization, which is more challenging, means to identify the pixels within each action frame that correspond to the action. This setting is usually referred to as pixel-level detection. In this chapter, we are using action, activity, event interchangeably.

preprint2020arXiv

An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models

Nowadays, autonomous driving has attracted much attention from both industry and academia. Convolutional neural network (CNN) is a key component in autonomous driving, which is also increasingly adopted in pervasive computing such as smartphones, wearable devices, and IoT networks. Prior work shows CNN-based classification models are vulnerable to adversarial attacks. However, it is uncertain to what extent regression models such as driving models are vulnerable to adversarial attacks, the effectiveness of existing defense techniques, and the defense implications for system and middleware builders. This paper presents an in-depth analysis of five adversarial attacks and four defense methods on three driving models. Experiments show that, similar to classification models, these models are still highly vulnerable to adversarial attacks. This poses a big security threat to autonomous driving and thus should be taken into account in practice. While these defense methods can effectively defend against different attacks, none of them are able to provide adequate protection against all five attacks. We derive several implications for system and middleware builders: (1) when adding a defense component against adversarial attacks, it is important to deploy multiple defense methods in tandem to achieve a good coverage of various attacks, (2) a blackbox attack is much less effective compared with a white-box attack, implying that it is important to keep model details (e.g., model architecture, hyperparameters) confidential via model obfuscation, and (3) driving models with a complex architecture are preferred if computing resources permit as they are more resilient to adversarial attacks than simple models.

preprint2020arXiv

Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI

Image registration is an ill-posed inverse problem which often requires regularisation on the solution space. In contrast to most of the current approaches which impose explicit regularisation terms such as smoothness, in this paper we propose a novel method that can implicitly learn biomechanics-informed regularisation. Such an approach can incorporate application-specific prior knowledge into deep learning based registration. Particularly, the proposed biomechanics-informed regularisation leverages a variational autoencoder (VAE) to learn a manifold for biomechanically plausible deformations and to implicitly capture their underlying properties via reconstructing biomechanical simulations. The learnt VAE regulariser then can be coupled with any deep learning based registration network to regularise the solution space to be biomechanically plausible. The proposed method is validated in the context of myocardial motion tracking on 2D stacks of cardiac MRI data from two different datasets. The results show that it can achieve better performance against other competing methods in terms of motion tracking accuracy and has the ability to learn biomechanical properties such as incompressibility and strains. The method has also been shown to have better generalisability to unseen domains compared with commonly used L2 regularisation schemes.

preprint2020arXiv

CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks

Neural architecture search (NAS) proves to be among the best approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and memory consumption. At the same time, 1-bit convolutional neural networks (CNNs) with binarized weights and activations show their potential for resource-limited embedded devices. One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework. To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent). In the search stage, the Child-Parent model uses an indicator generated by the child and parent model accuracy to evaluate the performance and abandon operations with less potential. In the training stage, a kernel-level CP loss is introduced to optimize the binarized network. Extensive experiments demonstrate that the proposed CP-NAS achieves a comparable accuracy with traditional NAS on both the CIFAR and ImageNet databases. It achieves the accuracy of $95.27\%$ on CIFAR-10, $64.3\%$ on ImageNet with binarized weights and activations, and a $30\%$ faster search than prior arts.

preprint2020arXiv

Density Map Guided Object Detection in Aerial Images

Object detection in high-resolution aerial images is a challenging task because of 1) the large variation in object size, and 2) non-uniform distribution of objects. A common solution is to divide the large aerial image into small (uniform) crops and then apply object detection on each small crop. In this paper, we investigate the image cropping strategy to address these challenges. Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that the object density map of an image presents how objects distribute in terms of the pixel intensity of the map. As pixel intensity varies, it is able to tell whether a region has objects or not, which in turn provides guidance for cropping images statistically. DMNet has three key components: a density map generation module, an image cropping module and an object detector. DMNet generates a density map and learns scale information based on density intensities to form cropping regions. Extensive experiments show that DMNet achieves state-of-the-art performance on two popular aerial image datasets, i.e. VisionDrone and UAVDT.

preprint2020arXiv

Enabling Cyberattack-Resilient Load Forecasting through Adversarial Machine Learning

In the face of an increasingly broad cyberattack surface, cyberattack-resilient load forecasting for electric utilities is both more necessary and more challenging than ever. In this paper, we propose an adversarial machine learning (AML) approach, which can respond to a wide range of attack behaviors without detecting outliers. It strikes a balance between enhancing a system's robustness against cyberattacks and maintaining a reasonable degree of forecasting accuracy when there is no attack. Attack models and configurations for the adversarial training were selected and evaluated to achieve the desired level of performance in a simulation study. The results validate the effectiveness and excellent performance of the proposed method.

preprint2020arXiv

Enhancing Review Comprehension with Domain-Specific Commonsense

Review comprehension has played an increasingly important role in improving the quality of online services and products and commonsense knowledge can further enhance review comprehension. However, existing general-purpose commonsense knowledge bases lack sufficient coverage and precision to meaningfully improve the comprehension of domain-specific reviews. In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs). We show that xSense KBs can be constructed inexpensively and present a knowledge distillation method that enables us to use xSense KBs along with BERT to boost the performance of various review comprehension tasks. We evaluate xSense over three review comprehension tasks: aspect extraction, aspect sentiment classification, and question answering. We find that xSense outperforms the state-of-the-art models for the first two tasks and improves the baseline BERT QA model significantly, demonstrating the usefulness of incorporating commonsense into review comprehension pipelines. To facilitate future research and applications, we publicly release three domain-specific knowledge bases and a domain-specific question answering benchmark along with this paper.

preprint2020arXiv

Gauge-induced Floquet topological states in photonic waveguides

Tremendous efforts have been devoted to the search for exotic topological states, which usually exist at an interface between lattices with differing topological invariants according to the bulk-edge correspondence. Here, we show a new finding of topological states localized at the interface between two gauge-shifted Floquet photonic lattices, despite the same topological order across the entire structure. The quasienergy band structures reveal that these new interface modes belong to the Floquet π modes, which are further found to enable a robust one-way propagation thanks to the flexible control of the Floquet gauge. The intriguing propagations of these π-interface modes are experimentally verified in a silicon waveguides platform at near-infrared wavelengths, which show both broad working bandwidth and high tolerance to the structural fluctuations. Our approach provides a new route for light manipulations with robust behaviours in Floquet engineering and beyond.

preprint2020arXiv

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. First, we sufficiently widen the deep thin network and train it until convergence. Then, we use this well-trained deep wide network to warm up (or initialize) the original deep thin network. This is achieved by layerwise imitation, that is, forcing the thin network to mimic the intermediate outputs of the wide network from layer to layer. Finally, we further fine tune this already well-initialized deep thin network. The theoretical guarantee is established by using the neural mean field analysis. It demonstrates the advantage of our layerwise imitation approach over backpropagation. We also conduct large-scale empirical experiments to validate the proposed method. By training with our method, ResNet50 can outperform ResNet101, and BERT Base can be comparable with BERT Large, when ResNet101 and BERT Large are trained under the standard training procedures as in the literature.

preprint2020arXiv

Improving operational flexibility of integrated energy system with uncertain renewable generations considering thermal inertia of buildings

Insufficient flexibility in system operation caused by traditional "heat-set" operating modes of combined heat and power (CHP) units in winter heating periods is a key issue that limits renewable energy consumption. In order to reduce the curtailment of renewable energy resources through improving the operational flexibility, a novel optimal scheduling model based on chance-constrained programming (CCP), aiming at minimizing the lowest generation cost, is proposed for a small-scale integrated energy system (IES) with CHP units, thermal power units, renewable generations and representative auxiliary equipments. In this model, due to the uncertainties of renewable generations including wind turbines and photovoltaic units, the probabilistic spinning reserves are supplied in the form of chance-constrained; from the perspective of user experience, a heating load model is built with consideration of heat comfort and inertia in buildings. To solve the model, a solution approach based on sequence operation theory (SOT) is developed, where the original CCP-based scheduling model is tackled into a solvable mixed-integer linear programming (MILP) formulation by converting a chance constraint into its deterministic equivalence class, and thereby is solved via the CPLEX solver. The simulation results on the modified IEEE 30-bus system demonstrate that the presented method manages to improve operational flexibility of the IES with uncertain renewable generations by comprehensively leveraging thermal inertia of buildings and different kinds of auxiliary equipments, which provides a fundamental way for promoting renewable energy consumption.

preprint2020arXiv

Lightweight image super-resolution with enhanced CNN

Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high computational cost and more memory storage for training a SR model, which limits their applications to SR with resource-constrained devices in real world. To resolve these problems, we propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB). Specifically, the IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. To remove redundant information obtained, a heterogeneous architecture is adopted in the IEEB. After that, the RB converts low-frequency features into high-frequency features by fusing global and local features, which is complementary with the IEEB in tackling the long-term dependency problem. Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image. The proposed LESRCNN can obtain a high-quality image by a model for different scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation. The code of LESRCNN is accessible on https://github.com/hellloxiaotian/LESRCNN.

preprint2020arXiv

MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly learn such a meta-policy. In this paper, we propose a new meta-RL algorithm called Meta Goal-generation for Hierarchical RL (MGHRL). Instead of directly generating policies over primitive action space for new tasks, MGHRL learns to generate high-level meta strategies over subgoals given past experience and leaves the rest of how to achieve subgoals as independent RL subtasks. Our empirical results on several challenging simulated robotics environments show that our method enables more efficient and generalized meta-learning from past experience.

preprint2020arXiv

Multi-Scale Progressive Fusion Network for Single Image Deraining

Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions, which makes it possible to exploit such complementary information for rain streak representation. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal. For similar rain streaks at different positions, we employ recurrent calculation to capture the global texture, thus allowing to explore the complementary and redundant information at the spatial dimension to characterize target rain streaks. Besides, we construct multi-scale pyramid structure, and further introduce the attention mechanism to guide the fine fusion of this correlated information from different scales. This multi-scale progressive fusion strategy not only promotes the cooperative representation, but also boosts the end-to-end training. Our proposed method is extensively evaluated on several benchmark datasets and achieves state-of-the-art results. Moreover, we conduct experiments on joint deraining, detection, and segmentation tasks, and inspire a new research direction of vision task-driven image deraining. The source code is available at \url{https://github.com/kuihua/MSPFN}.

preprint2020arXiv

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of sub-networks with different widths using different input resolutions to mutually learn multi-scale representations for each sub-network. It achieves consistently better ImageNet top-1 accuracy over the state-of-the-art adaptive network US-Net under different computation constraints, and outperforms the best compound scaled MobileNet in EfficientNet by 1.5%. The superiority of our method is also validated on COCO object detection and instance segmentation as well as transfer learning. Surprisingly, the training strategy of MutualNet can also boost the performance of a single network, which substantially outperforms the powerful AutoAugmentation in both efficiency (GPU search hours: 15000 vs. 0) and accuracy (ImageNet: 77.6% vs. 78.6%). Code is available at \url{https://github.com/taoyang1122/MutualNet}.

preprint2020arXiv

Nonlinear response properties in the inferior colliculus: Common sound-frequency dependence for linear and nonlinear responses

Neurons in the main center of convergence in the auditory midbrain, the central nucleus of the inferior colliculus (ICC) have been shown to display either linear significant receptive fields, or both, linear and nonlinear significant receptive fields. In this study, we used reverse correlation to probe linear and nonlinear response properties of single neurons in the cat ICC. The receptive fields display areas of stimulus parameters leading to enhanced or inhibited spiking activity, and thus allow investigating the interplay to process complex sounds. Spiking responses were obtained from neural recordings of anesthetized cats in response to dynamic moving ripple (DMR) stimuli. The DMR sound contains amplitude and frequency modulations and allows systematically mapping neural preferences. Correlations of the stimulus envelope that preferably excite neurons can be mapped with the spike-triggered covariance. The spike-triggered average and -covariance were computed for the envelope of the DMR, separately for each frequency carrier (spanning a range of 0-5.5 octaves). This enables studying processing of the sound envelope, and to investigate whether nonlinearities are more pronounced at the neurons' preferred frequencies rather than at other frequencies. We find that more than half of the neurons (n=120) display significant nonlinear response properties at least at one frequency carrier. Nonlinearities are dominant at the neuron's best frequency. The nonlinear preferences can have either the same or opposite temporal receptive field pattern (e.g. on-off) as the linear preferences. No relationship to other neural properties such as feature-selectivity, phase-locking, or the like has been found. Thus, these nonlinearities do not seem to be linked to a specific type of neuron but to be inherent to ICC neurons indicating a diverse range of filtering characteristics.

preprint2020arXiv

Nucleon elastic form factors at accessible large spacelike momenta

A Poincaré-covariant quark+diquark Faddeev equation is used to compute nucleon elastic form factors on $0\leq Q^2\leq 18 \,m_N^2$ ($m_N$ is the nucleon mass) and elucidate their role as probes of emergent hadronic mass in the Standard Model. The calculations expose features of the form factors that can be tested in new generation experiments at existing facilities, e.g. a zero in $G_E^p/G_M^p$; a maximum in $G_E^n/G_M^n$; and a zero in the proton's $d$-quark Dirac form factor, $F_1^d$. Additionally, examination of the associated light-front-transverse number and anomalous magnetisation densities reveals, inter alia: a marked excess of valence $u$-quarks in the neighbourhood of the proton's centre of transverse momentum; and that the valence $d$-quark is markedly more active magnetically than either of the valence $u$-quarks. The calculations and analysis also reveal other aspects of nucleon structure that could be tested with a high-luminosity accelerator capable of delivering higher beam energies than are currently available.

preprint2020arXiv

Observation of discrete conventional Caroli-de Gennes-Matricon states in the vortex core of single-layer FeSe/SrTiO3

Using low-temperature scanning tunneling microscopy (STM), we studied the vortex states of single-layer FeSe film on SrTiO3 (100) substrate, and the local behaviors of superconductivity at sample boundaries. We clearly observed multiple discrete Caroli-de Gennes-Matricon (CdGM) states in the vortex core, and quantitative analysis shows their energies well follow the formula: E = μΔ^2/E_F, where μ is a half integer and Δ is the mean superconducting gap over the Fermi surface. Meanwhile, a fully gapped spectrum without states near zero bias is observed at [110](Fe) oriented boundary of 1 ML and 2 ML FeSe films, and atomic step edge of 1 ML FeSe. Accompanied with theoretical calculations, our results indicate a s-wave pairing without sign-change in the high-TC FeSe_SrTiO3 superconductor.

preprint2020arXiv

Orthogonal electric control of the out-of-plane field-effect in two-dimensional ferroelectric alpha-In2Se3

Tuning the electric properties of crystalline solids is at the heart of material science and electronics. Generating the electric field-effect via an external voltage is a clean, continuous and systematic method. Here, utilizing the unique electric dipole locking in van der Waals (vdW) ferroelectric alpha-In2Se3, we report a new approach to establish the electric gating effect, where the electrostatic doping in the out-of-plane direction is induced and controlled by an in-plane voltage. With the vertical vdW heterostructure of ultrathin alpha-In2Se3 and MoS2, we validate an in-plane voltage gated coplanar field-effect transistor (CP-FET) with distinguished and retentive on/off ratio. Our results demonstrate unprecedented electric control of ferroelectricity, which paves the way for integrating two-dimensional (2D) ferroelectric into novel nanoelectronic devices with broad applications.

preprint2020arXiv

Outer-Product-Free Sets for Polynomial Optimization and Oracle-Based Cuts

This paper introduces cutting planes that involve minimal structural assumptions, enabling the generation of strong polyhedral relaxations for a broad class of problems. We consider valid inequalities for the set $S\cap P$, where $S$ is a closed set, and $P$ is a polyhedron. Given an oracle that provides the distance from a point to $S$, we construct a pure cutting plane algorithm which is shown to converge if the initial relaxation is a polyhedron. These cuts are generated from convex forbidden zones, or $S$-free sets, derived from the oracle. We also consider the special case of polynomial optimization. Accordingly we develop a theory of \emph{outer-product-free} sets, where $S$ is the set of real, symmetric matrices of the form $xx^T$. All maximal outer-product-free sets of full dimension are shown to be convex cones and we identify several families of such sets. These families are used to generate strengthened intersection cuts that can separate any infeasible extreme point of a linear programming relaxation efficiently. Computational experiments demonstrate the promise of our approach.

preprint2020arXiv

PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution

Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture. To further improve the performance of GAN based models on super-resolving face images, we propose PCA-SRGAN which pays attention to the cumulative discrimination in the orthogonal projection space spanned by PCA projection matrix of face data. By feeding the principal component projections ranging from structure to details into the discriminator, the discrimination difficulty will be greatly alleviated and the generator can be enhanced to reconstruct clearer contour and finer texture, helpful to achieve the high perception and low distortion eventually. This incremental orthogonal projection discrimination has ensured a precise optimization procedure from coarse to fine and avoids the dependence on the perceptual regularization. We conduct experiments on CelebA and FFHQ face datasets. The qualitative visual effect and quantitative evaluation have demonstrated the overwhelming performance of our model over related works.

preprint2020arXiv

PEARL: Plausibly Deniable Flash Translation Layer using WOM coding

When adversaries are powerful enough to coerce users to reveal encryption keys, encryption alone becomes insufficient for data protection. Plausible deniability (PD) mechanisms resolve this by enabling users to hide the mere existence of sensitive data, often by providing plausible "cover texts" or "public data volumes" hosted on the same device. Unfortunately, with the increasing prevalence of (NAND) flash as a high-performance cost-effective storage medium, PD becomes even more challenging in the presence of realistic adversaries who can usually access a device at multiple points in time ("multi-snapshot"). This is because read/write operations to flash do not result in intuitive corresponding changes to the underlying device state. The problem is further compounded by the fact that this behavior is mostly proprietary. For example, in a majority of commercially-available flash devices, an issued delete or overwrite operation from the upper layers almost certainly won't result in an actual immediate erase of the underlying flash cells. To address these challenges, we designed a new class of write-once memory (WOM) codes to store hidden bits in the same physical locations as other public bits. This is made possible by the inherent nature of NAND flash and the possibility of issuing multiple writes to target cells that have not previous been written to in existing pages. We designed PEARL, a general-purpose Flash Translation Layer (FTL) that allows users to plausibly deniably store hidden data in NAND flash devices. We implemented and evaluated PEARL on a widely used simulator FlashSim (Kim et al. 2019). PEARL performs well on real-world workloads, comparably to non-PD baselines. PEARL is the first system that achieves strong plausible deniability for NAND flash devices, secure against realistic multi-snapshot adversaries.

preprint2020arXiv

PrivColl: Practical Privacy-Preserving Collaborative Machine Learning

Collaborative learning enables two or more participants, each with their own training dataset, to collaboratively learn a joint model. It is desirable that the collaboration should not cause the disclosure of either the raw datasets of each individual owner or the local model parameters trained on them. This privacy-preservation requirement has been approached through differential privacy mechanisms, homomorphic encryption (HE) and secure multiparty computation (MPC), but existing attempts may either introduce the loss of model accuracy or imply significant computational and/or communicational overhead. In this work, we address this problem with the lightweight additive secret sharing technique. We propose PrivColl, a framework for protecting local data and local models while ensuring the correctness of training processes. PrivColl employs secret sharing technique for securely evaluating addition operations in a multiparty computation environment, and achieves practicability by employing only the homomorphic addition operations. We formally prove that it guarantees privacy preservation even though the majority (n-2 out of n) of participants are corrupted. With experiments on real-world datasets, we further demonstrate that PrivColl retains high efficiency. It achieves a speedup of more than 45X over the state-of-the-art MPC/HE based schemes for training linear/logistic regression, and 216X faster for training neural network.

preprint2020arXiv

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric. Owing to visual ambiguities, these content-based methods that determine the pairwise relationship only based on the similarity between them, inevitably produce a suboptimal ranking list. Instead, the pairwise similarity can be estimated more accurately along the geodesic path of the underlying data manifold by exploring the rich contextual information of the sample. In this paper, we propose a lightweight post-processing person re-identification method in which the pairwise measure is determined by the relationship between the sample and the counterpart's context in an unsupervised way. We translate the point-to-point comparison into the bilateral point-to-set comparison. The sample's context is composed of its neighbor samples with two different definition ways: the first order context and the second order context, which are used to compute the pairwise similarity in sequence, resulting in a progressive post-processing model. The experiments on four large-scale person re-identification benchmark datasets indicate that (1) the proposed method can consistently achieve higher accuracies by serving as a post-processing procedure after the content-based person re-identification methods, showing its state-of-the-art results, (2) the proposed lightweight method only needs about 6 milliseconds for optimizing the ranking results of one sample, showing its high-efficiency. Code is available at: https://github.com/123ci/PBCmodel.

preprint2020arXiv

Public discourse and sentiment during the COVID-19 pandemic: using Latent Dirichlet Allocation for topic modeling on Twitter

The study aims to understand Twitter users' discourse and psychological reactions to COVID-19. We use machine learning techniques to analyze about 1.9 million Tweets (written in English) related to coronavirus collected from January 23 to March 7, 2020. A total of salient 11 topics are identified and then categorized into ten themes, including "updates about confirmed cases," "COVID-19 related death," "cases outside China (worldwide)," "COVID-19 outbreak in South Korea," "early signs of the outbreak in New York," "Diamond Princess cruise," "economic impact," "Preventive measures," "authorities," and "supply chain." Results do not reveal treatments and symptoms related messages as prevalent topics on Twitter. Sentiment analysis shows that fear for the unknown nature of the coronavirus is dominant in all topics. Implications and limitations of the study are also discussed.

preprint2020arXiv

Realistic Adversarial Data Augmentation for MR Image Segmentation

Neural network-based approaches can achieve high accuracy in various medical image segmentation tasks. However, they generally require large labelled datasets for supervised learning. Acquiring and manually labelling a large medical dataset is expensive and sometimes impractical due to data sharing and privacy issues. In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation. Instead of generating pixel-wise adversarial attacks, our model generates plausible and realistic signal corruptions, which models the intensity inhomogeneities caused by a common type of artefacts in MR imaging: bias field. The proposed method does not rely on generative networks, and can be used as a plug-in module for general segmentation networks in both supervised and semi-supervised learning. Using cardiac MR imaging we show that such an approach can improve the generalization ability and robustness of models as well as provide significant improvements in low-data scenarios.

preprint2020arXiv

Recognizing Exercises and Counting Repetitions in Real Time

Artificial intelligence technology has made its way absolutely necessary in a variety of industries including the fitness industry. Human pose estimation is one of the important researches in the field of Computer Vision for the last few years. In this project, pose estimation and deep machine learning techniques are combined to analyze the performance and report feedback on the repetitions of performed exercises in real-time. Involving machine learning technology in the fitness industry could help the judges to count repetitions of any exercise during Weightlifting or CrossFit competitions.

preprint2020arXiv

RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices

Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices are urgently-needed in industry. The floating-point operations (FLOPs) of networks are not strictly proportional to the running speed on CPU devices, which inspires the design of an exactly "fast" and "accurate" object detector. After investigating the concern gaps between classification networks and detection backbones, and following the design principles of efficient networks, we propose a lightweight residual-like backbone with large receptive fields and wide dimensions for low-level features, which are crucial for detection tasks. Correspondingly, we also design a light-head detection part to match the backbone capability. Furthermore, by analyzing the drawbacks of current one-stage detector training strategies, we also propose three orthogonal training strategies---IOU-guided loss, classes-aware weighting method and balanced multi-task training approach. Without bells and whistles, our proposed RefineDetLite achieves 26.8 mAP on the MSCOCO benchmark at a speed of 130 ms/pic on a single-thread CPU. The detection accuracy can be further increased to 29.6 mAP by integrating all the proposed training strategies, without apparent speed drop.

preprint2020arXiv

Robust Federated Recommendation System

Federated recommendation systems can provide good performance without collecting users' private data, making them attractive. However, they are susceptible to low-cost poisoning attacks that can degrade their performance. In this paper, we develop a novel federated recommendation technique that is robust against the poisoning attack where Byzantine clients prevail. We argue that the key to Byzantine detection is monitoring of gradients of the model parameters of clients. We then propose a robust learning strategy where instead of using model parameters, the central server computes and utilizes the gradients to filter out Byzantine clients. Theoretically, we justify our robust learning strategy by our proposed definition of Byzantine resilience. Empirically, we confirm the efficacy of our robust learning strategy employing four datasets in a federated recommendation system.

preprint2020arXiv

Sorting-based Interactive Regret Minimization

As an important tool for multi-criteria decision making in database systems, the regret minimization query is shown to have the merits of top-k and skyline queries: it controls the output size while does not need users to provide any preferences. Existing researches verify that the regret ratio can be much decreased when interaction is available. In this paper, we study how to enhance current interactive regret minimization query by sorting mechanism. Instead of selecting the most favorite point from the displayed points for each interaction round, users sort the displayed data points and send the results to the system. By introducing sorting mechanism, for each round of interaction the utility space explored will be shrunk to some extent. Further the candidate points selection for following rounds of interaction will be narrowed to smaller data spaces thus the number of interaction rounds will be reduced. We propose two effective sorting-based algorithms namely Sorting-Simplex and Sorting-Random to find the maximum utility point based on Simplex method and randomly selection strategy respectively. Experiments on synthetic and real datasets verify our Sorting-Simplex and Sorting-Random algorithms outperform current state-of-art ones.

preprint2020arXiv

Stochastic Adaptive Line Search for Differentially Private Optimization

The performance of private gradient-based optimization algorithms is highly dependent on the choice of step size (or learning rate) which often requires non-trivial amount of tuning. In this paper, we introduce a stochastic variant of classic backtracking line search algorithm that satisfies Rényi differential privacy. Specifically, the proposed algorithm adaptively chooses the step size satsisfying the the Armijo condition (with high probability) using noisy gradients and function estimates. Furthermore, to improve the probability with which the chosen step size satisfies the condition, it adjusts per-iteration privacy budget during runtime according to the reliability of noisy gradient. A naive implementation of the backtracking search algorithm may end up using unacceptably large privacy budget as the ability of adaptive step size selection comes at the cost of extra function evaluations. The proposed algorithm avoids this problem by using the sparse vector technique combined with the recent privacy amplification lemma. We also introduce a privacy budget adaptation strategy in which the algorithm adaptively increases the budget when it detects that directions pointed by consecutive gradients are drastically different. Extensive experiments on both convex and non-convex problems show that the adaptively chosen step sizes allow the proposed algorithm to efficiently use the privacy budget and show competitive performance against existing private optimizers.

preprint2020arXiv

Twitter discussions and emotions about COVID-19 pandemic: a machine learning approach

The objective of the study is to examine coronavirus disease (COVID-19) related discussions, concerns, and sentiments that emerged from tweets posted by Twitter users. We analyze 4 million Twitter messages related to the COVID-19 pandemic using a list of 25 hashtags such as "coronavirus," "COVID-19," "quarantine" from March 1 to April 21 in 2020. We use a machine learning approach, Latent Dirichlet Allocation (LDA), to identify popular unigram, bigrams, salient topics and themes, and sentiments in the collected Tweets. Popular unigrams include "virus," "lockdown," and "quarantine." Popular bigrams include "COVID-19," "stay home," "corona virus," "social distancing," and "new cases." We identify 13 discussion topics and categorize them into five different themes, such as "public health measures to slow the spread of COVID-19," "social stigma associated with COVID-19," "coronavirus news cases and deaths," "COVID-19 in the United States," and "coronavirus cases in the rest of the world". Across all identified topics, the dominant sentiments for the spread of coronavirus are anticipation that measures that can be taken, followed by a mixed feeling of trust, anger, and fear for different topics. The public reveals a significant feeling of fear when they discuss the coronavirus new cases and deaths than other topics. The study shows that Twitter data and machine learning approaches can be leveraged for infodemiology study by studying the evolving public discussions and sentiments during the COVID-19. Real-time monitoring and assessment of the Twitter discussion and concerns can be promising for public health emergency responses and planning. Already emerged pandemic fear, stigma, and mental health concerns may continue to influence public trust when there occurs a second wave of COVID-19 or a new surge of the imminent pandemic.

preprint2020arXiv

Video Anomaly Detection for Smart Surveillance

In modern intelligent video surveillance systems, automatic anomaly detection through computer vision analytics plays a pivotal role which not only significantly increases monitoring efficiency but also reduces the burden on live monitoring. Anomalies in videos are broadly defined as events or activities that are unusual and signify irregular behavior. The goal of anomaly detection is to temporally or spatially localize the anomaly events in video sequences. Temporal localization (i.e. indicating the start and end frames of the anomaly event in a video) is referred to as frame-level detection. Spatial localization, which is more challenging, means to identify the pixels within each anomaly frame that correspond to the anomaly event. This setting is usually referred to as pixel-level detection. In this paper, we provide a brief overview of the recent research progress on video anomaly detection and highlight a few future research directions.

preprint2019arXiv

ANOVA Gaussian process modeling for high-dimensional stochastic computational models

In this paper we present a novel analysis of variance Gaussian process (ANOVA-GP) emulator for models governed by partial differential equations (PDEs) with high-dimensional random inputs. Gaussian process (GP) is a widely used surrogate modeling strategy, but it can become invalid when the inputs are high-dimensional. In this new ANOVA-GP strategy, high-dimensional inputs are decomposed into unions of local low-dimensional inputs, and principal component analysis (PCA) is applied to provide dimension reduction for each ANOVA term. We then systematically build local GP models for PCA coefficients based on ANOVA decomposition to provide an emulator for the overall high-dimensional problem. We present a general mathematical framework of ANOVA-GP, validate its accuracy and demonstrate its efficiency with numerical experiments.

preprint2019arXiv

Deep learning for cardiac image segmentation: A review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US) and major anatomical structures of interest (ventricles, atria and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

preprint2019arXiv

Improving Image Captioning with Conditional Generative Adversarial Nets

In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent evaluation problem among different objective language metrics, we are motivated to design some "discriminator" networks to automatically and progressively determine whether generated caption is human described or machine generated. Two kinds of discriminator architectures (CNN and RNN-based structures) are introduced since each has its own advantages. The proposed algorithm is generic so that it can enhance any existing RL-based image captioning framework and we show that the conventional RL training method is just a special case of our approach. Empirically, we show consistent improvements over all language evaluation metrics for different state-of-the-art image captioning models. In addition, the well-trained discriminators can also be viewed as objective image captioning evaluators

preprint2019arXiv

Improving the generalizability of convolutional neural network-based segmentation on CMR images

Convolutional neural network (CNN) based segmentation methods provide an efficient and automated way for clinicians to assess the structure and function of the heart in cardiac MR images. While CNNs can generally perform the segmentation tasks with high accuracy when training and test images come from the same domain (e.g. same scanner or site), their performance often degrades dramatically on images from different scanners or clinical sites. We propose a simple yet effective way for improving the network generalization ability by carefully designing data normalization and augmentation strategies to accommodate common scenarios in multi-site, multi-scanner clinical imaging data sets. We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy. Specifically, the method was trained on a large set of 3,975 subjects from the UK Biobank. It was then directly tested on 600 different subjects from the UK Biobank for intra-domain testing and two other sets for cross-domain testing: the ACDC dataset (100 subjects, 1 site, 2 scanners) and the BSCMR-AS dataset (599 subjects, 6 sites, 9 scanners). The proposed method produces promising segmentation results on the UK Biobank test set which are comparable to previously reported values in the literature, while also performing well on cross-domain test sets, achieving a mean Dice metric of 0.90 for the left ventricle, 0.81 for the myocardium and 0.82 for the right ventricle on the ACDC dataset; and 0.89 for the left ventricle, 0.83 for the myocardium on the BSCMR-AS dataset. The proposed method offers a potential solution to improve CNN-based model generalizability for the cross-scanner and cross-site cardiac MR image segmentation task.

preprint2019arXiv

Nature and Origins of Rich Complexes of C IV Associated Absorption Lines

Rich complexes of associated absorption lines (AALs) in quasar spectra provide unique information about gaseous infall, outflows, and feedback processes in quasar environments. We study five quasars at redshifts 3.1 to 4.4 with AAL complexes containing from 7 to 18 CIV 1548, 1551 systems in high-resolution spectra. These complexes span velocity ranges $\lesssim$3600 km/s within $\lesssim$8200 km/s of the quasar redshifts. All are highly ionised with no measurable low-ionisation ions like SiII or CII, and all appear to form in the quasar/host galaxy environments based on evidence for line locking, partial covering of the background light source, strong NV absorption, and/or roughly solar metallicities, and on the implausibility of such complexes forming in unrelated intervening galaxies. Most of the lines in all five complexes identify high-speed quasar-driven outflows at velocity shifts $v\lesssim -1000$ km/s. Four of the complexes also have lines at smaller blueshifted velocities that might form in ambient interstellar clouds, low-speed outflows or at feedback interfaces in the host galaxies where high-speed winds impact and shred interstellar clouds. The partial covering we measure in some of the high-speed outflow lines require small absorbing clouds with characteristic sizes $\lesssim$1 pc or $\lesssim$0.01 pc. The short survival times of these clouds require locations very close to the quasars, or cloud creation in situ at larger distances perhaps via feedback/cloud-shredding processes. The AAL complex in one quasar, J1008+3623, includes unusually narrow CIV systems at redshifted velocities $350\lesssim v\lesssim640$ km/s that are excellent candidates for gaseous infall towards the quasar, e.g., ''cold-mode" accretion or a gravitationally-bound galactic fountain.

preprint2019arXiv

Pion and Kaon Structure at the Electron-Ion Collider

Understanding the origin and dynamics of hadron structure and in turn that of atomic nuclei is a central goal of nuclear physics. This challenge entails the questions of how does the roughly 1 GeV mass-scale that characterizes atomic nuclei appear; why does it have the observed value; and, enigmatically, why are the composite Nambu-Goldstone (NG) bosons in quantum chromodynamics (QCD) abnormally light in comparison? In this perspective, we provide an analysis of the mass budget of the pion and proton in QCD; discuss the special role of the kaon, which lies near the boundary between dominance of strong and Higgs mass-generation mechanisms; and explain the need for a coherent effort in QCD phenomenology and continuum calculations, in exa-scale computing as provided by lattice QCD, and in experiments to make progress in understanding the origins of hadron masses and the distribution of that mass within them. We compare the unique capabilities foreseen at the electron-ion collider (EIC) with those at the hadron-electron ring accelerator (HERA), the only previous electron-proton collider; and describe five key experimental measurements, enabled by the EIC and aimed at delivering fundamental insights that will generate concrete answers to the questions of how mass and structure arise in the pion and kaon, the Standard Model's NG modes, whose surprisingly low mass is critical to the evolution of our Universe.

preprint2019arXiv

Radiality Constraints for Resilient Reconfiguration of Distribution Systems: Formulation and Application to Microgrid Formation

Network reconfiguration is an effective strategy for different purposes of distribution systems (DSs), e.g., resilience enhancement. In particular, DS automation, distributed generation integration and microgrid (MG) technology development, etc., are empowering much more flexible reconfiguration and operation of the system, e.g., DSs or MGs with flexible boundaries. However, the formulation of DS reconfiguration-related optimization problems to include those new flexibilities is non-trivial, especially for the issue of topology, which has to be radial. That is, existing methods of formulating radiality constraints can cause underutilization of DS flexibilities. Thus, this work proposes a new method for radiality constraints formulation fully enabling the topological and some other related flexibilities of DSs, so that the reconfiguration-related optimization problems can have extended feasibility and enhanced optimality. Graph-theoretic supports are provided to certify its theoretical validity. As integer variables are involved, we also analyze the tightness and compactness issues. The proposed radiality constraints are specifically applied to post-disaster MG formation, which is involved in many DS resilience-oriented service restoration and/or infrastructure recovery problems. The resulting new MG formation model, which allows more flexible merge and/or separation of sub-grids, etc., establishes superiority over the models in the literature. Case studies are conducted on two test systems.

preprint2019arXiv

Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation

In this work, we present a fully automatic method to segment cardiac structures from late-gadolinium enhanced (LGE) images without using labelled LGE data for training, but instead by transferring the anatomical knowledge and features learned on annotated balanced steady-state free precession (bSSFP) images, which are easier to acquire. Our framework mainly consists of two neural networks: a multi-modal image translation network for style transfer and a cascaded segmentation network for image segmentation. The multi-modal image translation network generates realistic and diverse synthetic LGE images conditioned on a single annotated bSSFP image, forming a synthetic LGE training set. This set is then utilized to fine-tune the segmentation network pre-trained on labelled bSSFP images, achieving the goal of unsupervised LGE image segmentation. In particular, the proposed cascaded segmentation network is able to produce accurate segmentation by taking both shape prior and image appearance into account, achieving an average Dice score of 0.92 for the left ventricle, 0.83 for the myocardium, and 0.88 for the right ventricle on the test set.

preprint2018arXiv

Resilient Disaster Recovery Logistics of Distribution Systems: Co-Optimize Service Restoration with Repair Crew and Mobile Power Source Dispatch

Repair crews (RCs) and mobile power sources (MPSs) are critical resources for distribution system (DS) outage management after a natural disaster. However, their logistics is not well investigated. We propose a resilient scheme for disaster recovery logistics to co-optimize DS restoration with dispatch of RCs and MPSs. A novel co-optimization model is formulated to route RCs and MPSs in the transportation network, schedule them in the DS, and reconfigure the DS for microgrid formation coordinately, etc. The model incorporates different timescales of DS restoration and RC/MPS dispatch, the coupling of transportation and power networks, etc. To ensure radiality of the DS with variable physical structure and MPS allocation, we also model topology constraints based on the concept of spanning forest. The model is convexified equivalently and linearized into a mixed-integer linear programming. To reduce its computation time, preprocessing methods are proposed to pre-assign a minimal set of repair tasks to depots and reduce the number of candidate nodes for MPS connection. Resilient recovery strategies thus are generated to enhance service restoration, especially by dynamic formation of microgrids that are powered by MPSs and topologized by repair actions of RCs and network reconfiguration of the DS. Case studies demonstrate the proposed methodology.

preprint2016arXiv

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method

The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work. Existing solutions to this problems largely rely on hand-craft features and vanishing lines, and they often fail in highly cluttered indoor rooms. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. The proposed FCN considers combines the layout contour property and the surface property so as to provide a robust estimate in the presence of cluttered objects. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. Our proposed system offers the state-of-the-art performance on two commonly used benchmark datasets.

preprint2016arXiv

GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes

An approach that extracts global attributes from outdoor images to facilitate geometric layout labeling is investigated in this work. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. First, by following a classical method, we use local features to provide initial labels for all super-pixels. Then, we develop a set of techniques to extract global attributes from 2D outdoor images. They include sky lines, ground lines, vanishing lines, etc. Finally, we propose the GAL system that integrates global attributes in the conditional random field (CRF) framework to improve initial labels so as to offer a more robust labeling result. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.

preprint2016arXiv

Hidden Phases Revealed at the Surface of Double-Layered Sr3(Ru1-xMnx)2O7

Double-layered Sr3Ru2O7 has received phenomenal consideration because it exhibits a plethora of exotic phases when perturbed. New phases emerge with the application of pressure, magnetic field, or doping. Here we show that creating a surface is an alternative and effective way to reveal hidden phases that are different from those seen in the bulk by investigating the surface properties of Sr3(Ru1-xMnx)2O7. Driven by the tilt distortion of RuO6 octahedra, the surface of Sr3Ru2O7 is less metallic than the bulk. In contrast, because of the vanishing of tilt and enhanced rotation with Mn-doping, the surface of Sr3(Ru0.84Mn0.16)2O7 is metallic while the bulk is insulating. Our result demonstrates that the electronic and structural properties at the surface are intimately coupled and consistent with quasi two-dimensional character.

preprint2016arXiv

HORNET: High-speed Onion Routing at the Network Layer

We present HORNET, a system that enables high-speed end-to-end anonymous channels by leveraging next generation network architectures. HORNET is designed as a low-latency onion routing system that operates at the network layer thus enabling a wide range of applications. Our system uses only symmetric cryptography for data forwarding yet requires no per-flow state on intermediate nodes. This design enables HORNET nodes to process anonymous traffic at over 93 Gb/s. HORNET can also scale as required, adding minimal processing overhead per additional anonymous channel. We discuss design and implementation details, as well as a performance and security evaluation.

preprint2016arXiv

Modeling Data-Plane Power Consumption of Future Internet Architectures

With current efforts to design Future Internet Architectures (FIAs), the evaluation and comparison of different proposals is an interesting research challenge. Previously, metrics such as bandwidth or latency have commonly been used to compare FIAs to IP networks. We suggest the use of power consumption as a metric to compare FIAs. While low power consumption is an important goal in its own right (as lower energy use translates to smaller environmental impact as well as lower operating costs), power consumption can also serve as a proxy for other metrics such as bandwidth and processor load. Lacking power consumption statistics about either commodity FIA routers or widely deployed FIA testbeds, we propose models for power consumption of FIA routers. Based on our models, we simulate scenarios for measuring power consumption of content delivery in different FIAs. Specifically, we address two questions: 1) which of the proposed FIA candidates achieves the lowest energy footprint; and 2) which set of design choices yields a power-efficient network architecture? Although the lack of real-world data makes numerous assumptions necessary for our analysis, we explore the uncertainty of our calculations through sensitivity analysis of input parameters.

preprint2016arXiv

Output Constraint Transfer for Kernelized Correlation Filter in Tracking

Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers. However, it does not reasonably model the distribution of correlation response during tracking process, which might cause the drifting problem, especially when targets undergo significant appearance changes due to occlusion, camera shaking, and/or deformation. In this paper, we propose an Output Constraint Transfer (OCT) method that by modeling the distribution of correlation response in a Bayesian optimization framework is able to mitigate the drifting problem. OCT builds upon the reasonable assumption that the correlation response to the target image follows a Gaussian distribution, which we exploit to select training samples and reduce model uncertainty. OCT is rooted in a new theory which transfers data distribution to a constraint of the optimized variable, leading to an efficient framework to calculate correlation filters. Extensive experiments on a commonly used tracking benchmark show that the proposed method significantly improves KCF, and achieves better performance than other state-of-the-art trackers. To encourage further developments, the source code is made available https://github.com/bczhangbczhang/OCT-KCF.

preprint2016arXiv

Unusual Fe-H bonding associated with oxygen vacancies at the (001) surface of Fe3O4

An unusual Fe-H bonding rather than conventional OH bonding is identified at Fe3O4 (001) surface. This abnormal behavior is associated with the oxygen vacancies which exist on the surface region but also penetrate deep into the bulk Fe3O4. In contrast, OH bonding becomes preferential as generally expected on an ozone processed surface, which has appreciably less oxygen vacancies. Such bonding site selective behavior, depending on oxygen vacancy concentrations, is further confirmed with DFT calculations. The results demonstrate an opportunity for tuning the chemical properties of oxide surfaces or oxide clusters.

preprint2016arXiv

Valence-quark distribution functions in the kaon and pion

We describe expressions for pion and kaon dressed-quark distribution functions that incorporate contributions from gluons which bind quarks into these mesons and hence overcome a flaw of the commonly used handbag approximation. The distributions therewith obtained are purely valence in character, ensuring that dressed-quarks carry all a meson's momentum at a characteristic hadronic scale and vanishing as $(1-x)^2$ when Bjorken-$x\to 1$. Comparing such distributions within the pion and kaon, it is apparent that the size of SU(3)-flavour symmetry breaking in meson parton distribution functions is modulated by the flavour dependence of dynamical chiral symmetry breaking. Corrections to these leading-order formulae may be divided into two classes, responsible for shifting dressed-quark momentum into glue and sea-quarks. Working with available empirical information, we build an algebraic framework that is capable of expressing the principal impact of both classes of corrections. This enables a realistic comparison with experiment which allows us to identify and highlight basic features of measurable pion and kaon valence-quark distributions. We find that whereas roughly two-thirds of the pion's light-front momentum is carried by valence dressed-quarks at a characteristic hadronic scale, this fraction rises to 95% in the kaon; evolving distributions with these features to a scale typical of available Drell-Yan data produces a kaon-to-pion ratio of u-quark distributions that is in agreement with the single existing data set; and predict a u-quark distribution within the pion that agrees with a modern reappraisal of $πN$ Drell-Yan data. Precise new data are essential in order to validate this reappraisal and because a single modest-quality measurement of the kaon-to-pion ratio cannot be considered definitive.

preprint2015arXiv

Contact-interaction Faddeev equation and, inter alia, proton tensor charges

A confining, symmetry-preserving, Dyson-Schwinger equation treatment of a vector-vector contact interaction is used to formulate Faddeev equations for the nucleon and Delta-baryon in which the kernel involves dynamical dressed-quark exchange and whose solutions therefore provide momentum-dependent Faddeev amplitudes. These solutions are compared with those obtained in the static approximation and with a QCD-kindred formulation of the Faddeev kernel. They are also used to compute a range of nucleon properties, amongst them: the proton's sigma-term; the large Bjorken-x values of separate ratios of unpolarised and longitudinally-polarised valence u- and d-quark parton distribution functions; and the proton's tensor charges, which enable one to directly determine the effect of dressed-quark electric dipole moments (EDMs) on neutron and proton EDMs.

preprint2015arXiv

Fast Iteratively Reweighted Least Squares Algorithms for Analysis-Based Sparsity Reconstruction

In this paper, we propose a novel algorithm for analysis-based sparsity reconstruction. It can solve the generalized problem by structured sparsity regularization with an orthogonal basis and total variation regularization. The proposed algorithm is based on the iterative reweighted least squares (IRLS) model, which is further accelerated by the preconditioned conjugate gradient method. The convergence rate of the proposed algorithm is almost the same as that of the traditional IRLS algorithms, that is, exponentially fast. Moreover, with the specifically devised preconditioner, the computational cost for each iteration is significantly less than that of traditional IRLS algorithms, which enables our approach to handle large scale problems. In addition to the fast convergence, it is straightforward to apply our method to standard sparsity, group sparsity, overlapping group sparsity and TV based problems. Experiments are conducted on a practical application: compressive sensing magnetic resonance imaging. Extensive results demonstrate that the proposed algorithm achieves superior performance over 14 state-of-the-art algorithms in terms of both accuracy and computational cost.

preprint2015arXiv

Kaon and pion parton distribution amplitudes to twist-three

We compute all kaon and pion parton distribution amplitudes (PDAs) to twist-three and find that only the pseudotensor PDA can reasonably be approximated by its conformal limit expression. At terrestrially accessible energy scales, the twist-two and pseudoscalar twist-three PDAs differ significantly from those functions commonly associated with their forms in QCD's conformal limit. In all amplitudes studied, SU(3) flavour-symmetry breaking is typically a 13% effect. This scale is determined by nonperturbative dynamics; namely, the current-quark-mass dependence of dynamical chiral symmetry breaking. The heavier-quark is favoured by this distortion, for example, support is shifted to the s-quark in the negative kaon. It appears, therefore, that at energy scales accessible with existing and foreseeable facilities, one may obtain reliable expectations for experimental outcomes by using these "strongly dressed" PDAs in formulae for hard exclusive processes. Following this procedure, any discrepancies between experiment and theory will be significantly smaller than those produced by using the conformal-limit PDAs. Moreover, the magnitude of any disagreement will either be a better estimate of higher-order, higher-twist effects or provide more realistic constraints on the Standard Model.

preprint2015arXiv

Macroscale boundary conditions for a non-linear heat exchanger

Multiscale modelling methodologies build macroscale models of materials with complicated fine microscale structure. We propose a methodology to derive boundary conditions for the macroscale model of a prototypical non-linear heat exchanger. The derived macroscale boundary conditions improve the accuracy of macroscale model. We verify the new boundary conditions by numerical methods. The techniques developed here can be adapted to a wide range of multiscale reaction-diffusion-advection systems.

preprint2015arXiv

Network Coding Tree Algorithm for Multiple Access System

Network coding is famous for significantly improving the throughput of networks. The successful decoding of the network coded data relies on some side information of the original data. In that framework, independent data flows are usually first decoded and then network coded by relay nodes. If appropriate signal design is adopted, physical layer network coding is a natural way in wireless networks. In this work, a network coding tree algorithm which enhances the efficiency of the multiple access system (MAS) is presented. For MAS, existing works tried to avoid the collisions while collisions happen frequently under heavy load. By introducing network coding to MAS, our proposed algorithm achieves a better performance of throughput and delay. When multiple users transmit signal in a time slot, the mexed signals are saved and used to jointly decode the collided frames after some component frames of the network coded frame are received. Splitting tree structure is extended to the new algorithm for collision solving. The throughput of the system and average delay of frames are presented in a recursive way. Besides, extensive simulations show that network coding tree algorithm enhances the system throughput and decreases the average frame delay compared with other algorithms. Hence, it improves the system performance.

preprint2015arXiv

SIRF: Simultaneous Image Registration and Fusion in A Unified Framework

In this paper, we propose a novel method for image fusion with a high-resolution panchromatic image and a low-resolution multispectral image at the same geographical location. The fusion is formulated as a convex optimization problem which minimizes a linear combination of a least-squares fitting term and a dynamic gradient sparsity regularizer. The former is to preserve accurate spectral information of the multispectral image, while the latter is to keep sharp edges of the high-resolution panchromatic image. We further propose to simultaneously register the two images during the fusing process, which is naturally achieved by virtue of the dynamic gradient sparsity property. An efficient algorithm is then devised to solve the optimization problem, accomplishing a linear computational complexity in the size of the output image in each iteration. We compare our method against seven state-of-the-art image fusion methods on multispectral image datasets from four satellites. Extensive experimental results demonstrate that the proposed method substantially outperforms the others in terms of both spatial and spectral qualities. We also show that our method can provide high-quality products from coarsely registered real-world datasets. Finally, a MATLAB implementation is provided to facilitate future research.

preprint2014arXiv

Forest Sparsity for Multi-channel Compressive Sensing

In this paper, we investigate a new compressive sensing model for multi-channel sparse data where each channel can be represented as a hierarchical tree and different channels are highly correlated. Therefore, the full data could follow the forest structure and we call this property as \emph{forest sparsity}. It exploits both intra- and inter- channel correlations and enriches the family of existing model-based compressive sensing theories. The proposed theory indicates that only $\mathcal{O}(Tk+\log(N/k))$ measurements are required for multi-channel data with forest sparsity, where $T$ is the number of channels, $N$ and $k$ are the length and sparsity number of each channel respectively. This result is much better than $\mathcal{O}(Tk+T\log(N/k))$ of tree sparsity, $\mathcal{O}(Tk+k\log(N/k))$ of joint sparsity, and far better than $\mathcal{O}(Tk+Tk\log(N/k))$ of standard sparsity. In addition, we extend the forest sparsity theory to the multiple measurement vectors problem, where the measurement matrix is a block-diagonal matrix. The result shows that the required measurement bound can be the same as that for dense random measurement matrix, when the data shares equal energy in each channel. A new algorithm is developed and applied on four example applications to validate the benefit of the proposed model. Extensive experiments demonstrate the effectiveness and efficiency of the proposed theory and algorithm.

preprint2014arXiv

On the decoupling of mirror fermions

We study an approach to chiral gauge theories on the lattice that involves decoupling "mirror" fermions from a vector-like theory. We have computed the polarization tensor in the "3-4-5" theory and find a directional discontinuity that appears to be nonzero in the continuum limit. This strongly suggests that the mirror fermions do not decouple.

preprint2013arXiv

Accurate Sampling Timing Acquisition for Baseband OFDM Power-line Communication in Non-Gaussian Noise

In this paper, a novel technique is proposed to address the joint sampling timing acquisition for baseband and broadband power-line communication (BB-PLC) systems using Orthogonal-Frequency-Division-Multiplexing (OFDM), including the sampling phase offset (SPO) and the sampling clock offset (SCO). Under pairwise correlation and joint Gaussian assumption of received signals in frequency domain, an approximated form of the log-likelihood function is derived. Instead of a high complexity two-dimension grid-search on the likelihood function, a five-step method is employed for accurate estimations. Several variants are presented in the same framework with different complexities. Unlike conventional pilot-assisted schemes using the extra phase rotations within one OFDM block, the proposed technique turns to the phase rotations between adjacent OFDM blocks. Analytical expressions of the variances and biases are derived. Extensive simulation results indicate significant performance improvements over conventional schemes. Additionally, effects of several noise models including non-Gaussianity, cyclo-stationarity, and temporal correlation are analyzed and simulated. Robustness of the proposed technique against violation of the joint Gaussian assumption is also verified by simulations.

preprint2013arXiv

Bottom-up Graphene Nanoribbon Field-Effect Transistors

Recently developed processes have enabled bottom-up chemical synthesis of graphene nanoribbons (GNRs) with precise atomic structure. These GNRs are ideal candidates for electronic devices because of their uniformity, extremely narrow width below 1 nm, atomically perfect edge structure, and desirable electronic properties. Here, we demonstrate nanoscale chemically synthesized GNR field-effect transistors, made possible by development of a new layer transfer process. We observe strong environmental sensitivity and unique transport behavior characteristic of sub-1nm width GNRs.

preprint2013arXiv

Elastic and transition form factors of the Δ(1232)

Predictions obtained with a confining, symmetry-preserving treatment of a vector-vector contact interaction at leading-order in a widely used truncation of QCD's Dyson-Schwinger equations are presented for Δand Ωbaryon elastic form factors and the γN -> Δtransition form factors. This simple framework produces results that are practically indistinguishable from the best otherwise available, an outcome which highlights that the key to describing many features of baryons and unifying them with the properties of mesons is a veracious expression of dynamical chiral symmetry breaking in the hadron bound-state problem. The following specific results are of particular interest. The Δelastic form factors are very sensitive to m_Δ. Hence, given that the parameters which define extant simulations of lattice-regularised QCD produce Δ-resonance masses that are very large, the form factors obtained therewith are a poor guide to properties of the Δ(1232). Considering the Δ-baryon's quadrupole moment, whilst all computations produce a negative value, the conflict between theoretical predictions entails that it is currently impossible to reach a sound conclusion on the nature of the Δ-baryon's deformation in the infinite momentum frame. Results for analogous properties of the Ωbaryon are less contentious. In connection with the N->Δtransition, the Ash-convention magnetic transition form factor falls faster than the neutron's magnetic form factor and nonzero values for the associated quadrupole ratios reveal the impact of quark orbital angular momentum within the nucleon and Δ; and, furthermore, these quadrupole ratios do slowly approach their anticipated asymptotic limits.

preprint2013arXiv

Insights into the gamma* N -> Delta transition

The γ* N -> Δ(1232) transition is a window on hadron shape deformation, the applicability of perturbative QCD at moderate momentum transfers, and the influence of nonperturbative phenomena on hadronic observables. We explain that the Ash-convention magnetic transition form factor must fall faster than the neutron's magnetic form factor and nonzero values for the associated quadrupole ratios reveal the impact of quark orbital angular momentum within the nucleon and Δ(1232); and show that these quadrupole ratios do approach their predicted asymptotic limits, albeit slowly.

preprint2013arXiv

On the decoupling of mirror fermions

An approach to the formulation of chiral gauge theories on the lattice is to start with a vector-like theory, but decouple one chirality (the "mirror" fermions) using strong Yukawa interactions with a chirally coupled "Higgs" field. While this is an attractive idea, its viability needs to be tested with nonperturbative studies. The model that we study here, the so-called "3-4-5" model, is anomaly free and the presence of massless states in the mirror sector is not required by anomaly matching arguments, in contrast to the "1-0" model that was studied previously. We have computed the polarization tensor in this theory and find a directional discontinuity that appears to be nonzero in the limit of an infinite lattice, which is equivalent to the continuum limit at fixed physical volume. We show that a similar behavior occurs for the free massless Ginsparg-Wilson fermion, where the polarization tensor is known to have a directional discontinuity in the continuum limit. We thus find support for the conclusion that in the continuum limit of the 3-4-5 model, there are massless charged modes in the mirror sector so that it does not decouple from the light sector. The value of the discontinuity we obtain allows for two interpretations: either a chiral gauge theory does not emerge and mirror-sector fermions in a chiral anomaly free representation remain massless, or a massless vectorlike mirror fermion appears. We end by discussing some questions for future study.

preprint2012arXiv

Challenging the Long Tail Recommendation

The success of "infinite-inventory" retailers such as Amazon.com and Netflix has been largely attributed to a "long tail" phenomenon. Although the majority of their inventory is not in high demand, these niche products, unavailable at limited-inventory competitors, generate a significant fraction of total revenue in aggregate. In addition, tail product availability can boost head sales by offering consumers the convenience of "one-stop shopping" for both their mainstream and niche tastes. However, most of existing recommender systems, especially collaborative filter based methods, can not recommend tail products due to the data sparsity issue. It has been widely acknowledged that to recommend popular products is easier yet more trivial while to recommend long tail products adds more novelty yet it is also a more challenging task. In this paper, we propose a novel suite of graph-based algorithms for the long tail recommendation. We first represent user-item information with undirected edge-weighted graph and investigate the theoretical foundation of applying Hitting Time algorithm for long tail item recommendation. To improve recommendation diversity and accuracy, we extend Hitting Time and propose efficient Absorbing Time algorithm to help users find their favorite long tail items. Finally, we refine the Absorbing Time algorithm and propose two entropy-biased Absorbing Cost algorithms to distinguish the variation on different user-item rating pairs, which further enhances the effectiveness of long tail recommendation. Empirical experiments on two real life datasets show that our proposed algorithms are effective to recommend long tail items and outperform state-of-the-art recommendation techniques.

preprint2012arXiv

Features and flaws of a contact interaction treatment of the kaon

Elastic and semileptonic transition form factors for the kaon and pion are calculated using the leading-order in a global-symmetry-preserving truncation of the Dyson-Schwinger equations and a momentum-independent form for the associated kernels in the gap and Bethe-Salpeter equations. The computed form factors are compared both with those obtained using the same truncation but an interaction that preserves the one-loop renormalisation-group behaviour of QCD and with data. The comparisons show that: in connection with observables revealed by probes with |Q^2|<~ M^2, where M~0.4GeV is an infrared value of the dressed-quark mass, results obtained using a symmetry-preserving regularisation of the contact-interaction are not realistically distinguishable from those produced by more sophisticated kernels; and available data on kaon form factors do not extend into the domain whereupon one could distinguish between the interactions. The situation is different if one includes the domain Q^2>M^2. Thereupon, a fully consistent treatment of the contact interaction produces form factors that are typically harder than those obtained with QCD renormalisation-group-improved kernels. Amongst other things also described are a Ward identity for the inhomogeneous scalar vertex, similarity between the charge distribution of a dressed-u-quark in the K^+ and that of the dressed-u-quark in the pi^+, and reflections upon the point whereat one might begin to see perturbative behaviour in the pion form factor. Interpolations of the form factors are provided, which should assist in working to chart the interaction between light-quarks by explicating the impact on hadron properties of differing assumptions about the behaviour of the Bethe-Salpeter kernel.

preprint2012arXiv

Fine Residual Carrier Frequency and Sampling Frequency Estimation in Wireless OFDM Systems

This paper presents a novel algorithm for residual phase estimation in wireless OFDM systems, including the carrier frequency offset (CFO) and the sampling frequency offset (SFO). The subcarriers are partitioned into several regions which exhibit pairwise correlations. The phase increment between successive OFDM blocks is exploited which can be estimated by two estimators with different computational loads. Numerical results of estimation variance are presented. Simulations indicate performance improvement of the proposed technique over several conventional schemes in a multipath channel.

preprint2012arXiv

Spectrum of hadrons with strangeness

We describe a calculation of the spectrum of strange and nonstrange hadrons that simultaneously correlates the dressed-quark-core masses of meson and baryon ground- and excited-states within a single framework. The foundation for this analysis is a symmetry-preserving Dyson-Schwinger equation treatment of a vector-vector contact interaction. Our results exemplify and highlight the deep impact of dynamical chiral symmetry breaking on the hadron spectrum: an accurate description of the meson spectrum entails a similarly successful prediction of the spectrum of baryons, including those with strangeness. The analysis also provides numerous insights into baryon structure. For example, that baryon structure is largely flavour-blind, the first radial excitation of ground-state baryons is constituted almost entirely from axial-vector diquark correlations, and DCSB is the foundation for the ordering of low-lying baryon levels; viz., (1/2)^+, (1/2)^+, (1/2)^-.

preprint2011arXiv

Supercurrent conservation in the lattice Wess-Zumino model with Ginsparg-Wilson fermions

We study supercurrent conservation for the four-dimensional Wess-Zumino model formulated on the lattice. The formulation is one that has been discussed several times, and uses Ginsparg-Wilson fermions of the overlap (Neuberger) variety, together with an auxiliary fermion (plus superpartners), such that a lattice version of U(1)_R symmetry is exactly preserved in the limit of vanishing bare mass. We show that the almost naive supercurrent is conserved at one loop. By contrast we find that this is not true for Wilson fermions and a canonical scalar action. We provide nonperturbative evidence for the nonconservation of the supercurrent in Monte Carlo simulations.

preprint2010arXiv

Lattice Wess-Zumino model with Ginsparg-Wilson fermions: One-loop results and GPU benchmarks

We numerically evaluate the one-loop counterterms for the four-dimensional Wess-Zumino model formulated on the lattice using Ginsparg-Wilson fermions of the overlap (Neuberger) variety, together with an auxiliary fermion (plus superpartners), such that a lattice version of $U(1)_R$ symmetry is exactly preserved in the limit of vanishing bare mass. We confirm previous findings by other authors that at one loop there is no renormalization of the superpotential in the lattice theory, but that there is a mismatch in the wavefunction renormalization of the auxiliary field. We study the range of the Dirac operator that results when the auxiliary fermion is integrated out, and show that localization does occur, but that it is less pronounced than the exponential localization of the overlap operator. We also present preliminary simulation results for this model, and outline a strategy for nonperturbative improvement of the lattice supercurrent through measurements of supersymmetry Ward identities. Related to this, some benchmarks for our graphics processing unit code are provided. Our simulation results find a nearly vanishing vacuum expectation value for the auxiliary field, consistent with approximate supersymmetry at weak coupling.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Source provenance

Where this author record came from

arxivconfidence 95%

external id: arxiv:2512.24970:author:1:chen-chen

Imported May 21, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2509.02110:author:1:chen-chen

Imported May 21, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2605.10001:author:3:chen-chen

Imported May 20, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2605.15235:author:4:chen-chen

Imported May 20, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2605.16815:author:3:chen-chen

Imported May 20, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2604.28123:author:8:chen-chen