Researcher profile

Jun Liu

Jun Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

98works

0followers

43topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

preprint2026arXiv

Continuous-tone Simple Points: An $\ell_0$-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation

Topological features play an essential role in ensuring geometric plausibility and structural consistency in image analysis tasks such as segmentation and skeletonization. However, integrating topology-preserving learning based on simple points into deep learning tasks remains challenging, as existing simple point detection methods are confined to binary images and are non-differentiable, rendering them incompatible with gradient-based optimization in modern deep learning. Moreover, morphological and purely data-driven approaches often fail to guaranty topological consistency. To address these limitations, we propose a novel method that directly computes simple points on continuous-valued images, enabling differentiable topological inference. Building on this theory, we develop an efficient skeleton extraction algorithm that preserves topological structures in binary and continuous-valued images. Furthermore, we design a variational model that enforces topological constraints by preserving topologically non-removable (i.e., non-simple) points, which can be seamlessly integrated into any deep neural network segmentation with softmax or sigmoid outputs. Experimental results demonstrate that the proposed approach effectively improves topological integrity and structural accuracy across multiple benchmarks. The codes are available in https://github.com/levnsio/CSP.

preprint2026arXiv

FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution and atmospheric seeing, which imposes a stochastic, spatially varying PSF that cannot be resolved through upsampling alone. Existing methods rely on synthetic training pairs that fail to capture real atmospheric statistics and are prone to either over-smoothed reconstructions or hallucination sources with no physical counterpart in the observed sky. We propose FluxFlow, a conservative pixel-space flow-matching framework that incorporates observation uncertainty and source-region importance weights during training, and a training-free Wiener-regularized test-time correction to suppress hallucination sources while preserving recovered detail. We further construct the DESI--HST Dataset, the large-scale real-world benchmark comprising 19,500 real co-registered ground-to-space image pairs with real atmospheric PSF variation. Experiments demonstrate that FluxFlow consistently outperforms existing baseline methods in both photometric and scientific accuracy.

preprint2026arXiv

MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions

Analyzing microscopy images to extract biological object properties (e.g., their morphological organization, temporal dynamics, and population density) is fundamental to various biomedical research. Yet conducting this manually is costly and time-consuming. Though deep learning-based approaches have been explored to automate this process, the substantial diversity of microscopy analysis settings in practice (including variations of biological object types, sample processing protocols, imaging equipment, and analysis tasks, etc.) often renders them ineffective. As a result, these approaches typically require extensive adaptation for different settings, which, however, can impose burdens that are often practically unsustainable for laboratories, forcing biomedical researchers to still commonly rely on manual analysis, thereby severely bottlenecking the pace of biomedical research progress. This situation has created a pressing and long-standing need for a reliable and broadly applicable microscopy image analysis tool, yet such a tool is still missing. To address this gap, we present the first ready-to-use microscopy image analysis framework, MicroscopyMatching, that can reliably perform key analysis tasks (including segmentation, tracking, and counting) across diverse microscopy analysis settings. From a fundamentally different perspective, MicroscopyMatching reformulates diverse microscopy image analysis tasks as a unified matching problem, effectively handling this problem by exploiting the robust matching capability from pre-trained latent diffusion models.

preprint2025arXiv

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD. This is achieved through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity. At its core, a lightweight dynamic routing network guides expert specialization during training through a diversity enhancing objective, encouraging complementary expertise among experts. Additionally, the routing network adaptively learns to activate only the most relevant experts, thereby improving detection performance while minimizing computational overhead during inference. Comprehensive experiments on five large-scale benchmarks demonstrate the superiority of YOLO-Master. On MS COCO, our model achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference. Notably, the gains are most pronounced on challenging dense scenes, while the model preserves efficiency on typical inputs and maintains real-time inference speed. Code will be available.

preprint2024arXiv

FlashDecoding++: Faster Large Language Model Inference on GPUs

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Performance loss due to static dataflow. Kernel performance in LLM depends on varied input data features, hardware configurations, etc. A single and static dataflow may lead to a 50.25% performance loss for GEMMs of different shapes in LLM inference. We present FlashDecoding++, a fast LLM inference engine supporting mainstream LLMs and hardware back-ends. To tackle the above challenges, FlashDecoding++ creatively proposes: (1) Asynchronized softmax with unified max value. FlashDecoding++ introduces a unified max value technique for different partial softmax computations to avoid synchronization. (2) Flat GEMM optimization with double buffering. FlashDecoding++ points out that flat GEMMs with different shapes face varied bottlenecks. Then, techniques like double buffering are introduced. (3) Heuristic dataflow with hardware resource adaptation. FlashDecoding++ heuristically optimizes dataflow using different hardware resource considering input dynamics. Due to the versatility of optimizations in FlashDecoding++, FlashDecoding++ can achieve up to 4.86x and 2.18x speedup on both NVIDIA and AMD GPUs compared to Hugging Face implementations. FlashDecoding++ also achieves an average speedup of 1.37x compared to state-of-the-art LLM inference engines on mainstream LLMs.

preprint2024arXiv

FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and quantization are commonly used to mitigate the gap between LLM's computation/memory overheads and hardware capacity. However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads. This paper proposes FlightLLM, enabling efficient LLMs inference with a complete mapping flow on FPGAs. In FlightLLM, we highlight an innovative solution that the computation and memory overhead of LLMs can be solved by utilizing FPGA-specific resources (e.g., DSP48 and heterogeneous memory hierarchy). We propose a configurable sparse DSP chain to support different sparsity patterns with high computation efficiency. Second, we propose an always-on-chip decode scheme to boost memory bandwidth with mixed-precision support. Finally, to make FlightLLM available for real-world LLMs, we propose a length adaptive compilation method to reduce the compilation overhead. Implemented on the Xilinx Alveo U280 FPGA, FlightLLM achieves 6.0$\times$ higher energy efficiency and 1.8$\times$ better cost efficiency against commercial GPUs (e.g., NVIDIA V100S) on modern LLMs (e.g., LLaMA2-7B) using vLLM and SmoothQuant under the batch size of one. FlightLLM beats NVIDIA A100 GPU with 1.2$\times$ higher throughput using the latest Versal VHK158 FPGA.

preprint2023arXiv

Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text

Logical reasoning task involves diverse types of complex reasoning over text, based on the form of multiple-choice question answering. Given the context, question and a set of options as the input, previous methods achieve superior performances on the full-data setting. However, the current benchmark dataset has the ideal assumption that the reasoning type distribution on the train split is close to the test split, which is inconsistent with many real application scenarios. To address it, there remain two problems to be studied: (1) How is the zero-shot capability of the models (train on seen types and test on unseen types)? (2) How to enhance the perception of reasoning types for the models? For problem 1, we propose a new benchmark for generalized zero-shot logical reasoning, named ZsLR. It includes six splits based on the three type sampling strategies. For problem 2, a type-aware model TaCo is proposed. It utilizes both the heuristic input reconstruction and the contrastive learning to improve the type perception in the global representation. Extensive experiments on both the zero-shot and full-data settings prove the superiority of TaCo over the state-of-the-art methods. Also, we experiment and verify the generalization capability of TaCo on other logical reasoning dataset.

preprint2023arXiv

Modeling Uncertain Feature Representation for Domain Generalization

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Existing methods commonly consider feature statistics as deterministic values measured from the learned features and do not explicitly model the uncertain statistics discrepancy caused by potential domain shifts during testing. In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i.e., characterizing the feature statistics as uncertain distributions during training. Specifically, we hypothesize that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution. During inference, we propose an instance-wise adaptation strategy that can adaptively deal with the unforeseeable shift and further enhance the generalization ability of the trained model with negligible additional cost. We also conduct theoretical analysis on the aspects of generalization error bound and the implicit regularization effect, showing the efficacy of our method. Extensive experiments demonstrate that our method consistently improves the network generalization ability on multiple vision tasks, including image classification, semantic segmentation, instance retrieval, and pose estimation. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints. Code will be released in https://github.com/lixiaotong97/DSU.

preprint2023arXiv

The grand picture behind Jensen's inequality

Let $I$ and $J$ be two intervals, and let $f, g: I \rightarrow \mathbb{R}$. If for any points $a$ and $b$ in $I$ and any positive numbers $p$ and $q$ such that $p + q = 1$, we have \begin{align} \nonumber p f(a) + q f(b) + g(pa + qb) \in J, \end{align} then for any points $x_{1}, \ldots, x_{n}$ in $I$ and any positive numbers $λ_{1}, \ldots, λ_{n}$ such that $\sum_{i=1}^{n}λ_{i} = 1$, we have \begin{align} \nonumber \sum_{i=1}^{n}λ_{i} f(x_{i}) + g\left( \sum_{i=1}^{n}λ_{i}x_{i} \right) \in J. \end{align} If we take $g = -f$ and $J = [0, +\infty)$, then the Jensen's inequality. The conclusion is only a short glimpse of the grand picture behind Jensen's inequality shows in this paper.

preprint2023arXiv

The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge

Automatic intracranial hemorrhage segmentation in 3D non-contrast head CT (NCCT) scans is significant in clinical practice. Existing hemorrhage segmentation methods usually ignores the anisotropic nature of the NCCT, and are evaluated on different in-house datasets with distinct metrics, making it highly challenging to improve segmentation performance and perform objective comparisons among different methods. The INSTANCE 2022 was a grand challenge held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing. The INSTANCE released a training set of 100 cases with ground-truth and a validation set with 30 cases without ground-truth labels that were available to the participants. A held-out testing set with 70 cases is utilized for the final evaluation and ranking. The methods from different participants are ranked based on four metrics, including Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), Relative Volume Difference (RVD) and Normalized Surface Dice (NSD). A total of 13 teams submitted distinct solutions to resolve the challenges, making several baseline models, pre-processing strategies and anisotropic data processing techniques available to future researchers. The winner method achieved an average DSC of 0.6925, demonstrating a significant growth over our proposed baseline method. To the best of our knowledge, the proposed INSTANCE challenge releases the first intracranial hemorrhage segmentation benchmark, and is also the first challenge that intended to resolve the anisotropic problem in 3D medical image segmentation, which provides new alternatives in these research fields.

preprint2022arXiv

A Boundary Regression Model for Nested Named Entity Recognition

Recognizing named entities (NEs) is commonly conducted as a classification problem that predicts a class tag for a word or a NE candidate in a sentence. In shallow structures, categorized features are weighted to support the prediction. Recent developments in neural networks have adopted deep structures that map categorized features into continuous representations. This approach unfolds a dense space saturated with high-order abstract semantic information, where the prediction is based on distributed feature representations. In this paper, positions of NEs in a sentence are represented as continuous values. Then, a regression operation is introduced to regress boundaries of NEs in a sentence. Based on boundary regression, we design a boundary regression model to support nested NE recognition. It is a multiobjective learning framework, which simultaneously predicts the classification score of a NE candidate and refine its spatial location in a sentence. It has the advantage to resolve nested NEs and support boundary regression for locating NEs in a sntence. By sharing parameters for predicting and locating, this model enables more potent nonlinear function approximators to enhance model discriminability. Experiments demonstrate state-of-the-art performance for nested NE recognition\footnote{Our codes to implement the BR model are available at: \url{https://github.com/wuyuefei3/BR}.}.

preprint2022arXiv

A Direct Parallel-in-Time Quasi-Boundary Value Method for Inverse Space-Dependent Source Problems

Inverse source problems arise often in real-world applications, such as localizing unknown groundwater contaminant sources. Being different from Tikhonov regularization, the quasi-boundary value method has been proposed and analyzed as an effective way for regularizing such inverse source problems, which was shown to achieve an optimal order convergence rate under suitable assumptions. However, fast direct or iterative solvers for the resulting all-at-once large-scale linear systems have been rarely studied in the literature. In this work, we first proposed and analyzed a modified quasi-boundary value method, and then developed a diagonalization-based parallel-in-time (PinT) direct solver, which can achieve a dramatic speedup in CPU times when compared with MATLAB's sparse direct solver. In particular, the time-discretization matrix $B$ is shown to be diagonalizable, and the condition number of its eigenvector matrix $V$ is proven to exhibit quadratic growth, which guarantees the roundoff errors due to diagonalization is well controlled. Several 1D and 2D examples are presented to demonstrate the very promising computational efficiency of our proposed method, where the CPU times in 2D cases can be speedup by three orders of magnitude.

preprint2022arXiv

A Fast Algorithm for Robust Action Selection in Multi-Agent Systems

In this paper, we consider a robust action selection problem in multi-agent systems where performance must be guaranteed when the system suffers a worst-case attack on its agents. Specifically, agents are tasked with selecting actions from a common ground set according to individualized objective functions, and we aim to protect the system against attacks. In our problem formulation, attackers attempt to disrupt the system by removing an agent's contribution after knowing the system solution and thus can attack perfectly. To protect the multi-agent system against such attacks, we aim to maximize the minimum performance of all agents' individual objective functions under attacks. Thus, we propose a fast algorithm with tunable parameters for balancing complexity and performance, yielding substantially improved time complexity and performance compared to recent methods. Finally, we provide Monte Carlo simulations to demonstrate the performance of the proposed algorithm.

preprint2022arXiv

A Piecewise Learning Framework for Control of Unknown Nonlinear Systems with Stability Guarantees

We propose a piecewise learning framework for controlling nonlinear systems with unknown dynamics. While model-based reinforcement learning techniques in terms of some basis functions are well known in the literature, when it comes to more complex dynamics, only a local approximation of the model can be obtained using a limited number of bases. The complexity of the identifier and the controller can be considerably high if obtaining an approximation over a larger domain is desired. To overcome this limitation, we propose a general piecewise nonlinear framework where each piece is responsible for locally learning and controlling over some region of the domain. We obtain rigorous uncertainty bounds for the learned piecewise models. The piecewise affine (PWA) model is then studied as a special case, for which we propose an optimization-based verification technique for stability analysis of the closed-loop system. Accordingly, given a time-discretization of the learned {PWA} system, we iteratively search for a common piecewise Lyapunov function in a set of positive definite functions, where a non-monotonic convergence is allowed. This Lyapunov candidate is verified on the uncertain system to either provide a certificate for stability or find a counter-example when it fails. This counter-example is added to a set of samples to facilitate the further learning of a Lyapunov function. We demonstrate the results on two examples and show that the proposed approach yields a less conservative region of attraction (ROA) compared with alternative state-of-the-art approaches. Moreover, we provide the runtime results to demonstrate potentials of the proposed framework in real-world implementations.

preprint2022arXiv

A special cross-tie domain wall in helimagnet

A special cross-tie (SCT) domain wall was discovered in the helimagnet MnCoSi alloy via the magnetic vector field tomography in Lorentz transmission electron microscopy (LTEM). Different to the traditional cross-tie (TCT) domain wall where the convergent/divergent magnetic moment configuration line up one by one, the relative large Bloch type sub-walls emerge in this brand-new SCT domain wall and two mutually perpendicular rotation axes coexist in this special feature. The straight magnetic stripes accompanied with the unraveled domain walls hint the complex mechanism to form this SCT structure. Interestingly, different orientation of this domain wall in LTEM can easily exhibit various magnetic features, including meron/antimeron chains or bimeron strings.

preprint2022arXiv

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

This paper proposes a specification-guided framework for control of nonlinear systems with linear temporal logic (LTL) specifications. In contrast with well-known abstraction-based methods, the proposed framework directly characterizes the winning set, i.e., the set of initial conditions from which a given LTL formula can be realized, over the continuous state space of the system via a monotonic operator. Following this characterization, an algorithm is proposed to practically approximate the operator via an adaptive interval subdivision scheme, which yields a finite-memory control strategy. We show that the proposed algorithm is sound for full LTL specifications, and robustly complete for specifications recognizable by deterministic Büchi automata (DBA), the latter in the sense that control strategies can be found whenever the given specification can be satisfied with additional bounded disturbances. Without having to compute and store the abstraction and the resulting product system with the DBA, the proposed method is more memory efficient, which is demonstrated by complexity analysis and performance tests. A pre-processing stage is also devised to reduce computational cost via a decomposition of the specification. We show that the proposed method can effectively solve real-world control problems such as jet engine compressor control and motion planning for manipulators and mobile robots.

preprint2022arXiv

A Vanka-type multigrid solver for complex-shifted Laplacian systems from diagonalization-based parallel-in-time algorithms

We propose and analyze a Vanka-type multigrid solver for solving a sequence of complex-shifted Laplacian systems arising in diagonalization-based parallel-in-time algorithms for evolutionary equations. Under suitable assumption, local Fourier analysis shows the proposed Vanka-type smoother achieves a uniform smoothing factor, which is verified by several numerical examples.

preprint2022arXiv

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks, and also limited variations in environmental conditions and viewpoints. To address these limitations, we create a large and diverse dataset, Animal Kingdom, that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footages used in our dataset record different times of the day in extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes. Such a challenging and comprehensive dataset shall be able to facilitate the community to develop, adapt, and evaluate various types of advanced methods for animal behavior analysis. Moreover, we propose a Collaborative Action Recognition (CARe) model that learns general and specific features for action recognition with unseen new animals. This method achieves promising performance in our experiments. Our dataset can be found at https://sutdcv.github.io/Animal-Kingdom.

preprint2022arXiv

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the target domain. Existing methods commonly consider the source and target domains are isolated from each other, i.e., no intermediate status is modeled between both domains. Directly transferring the knowledge between two isolated domains can be very difficult, especially when the domain gap is large. From a novel perspective, we assume these two domains are not completely isolated, but can be connected through intermediate domains. Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer. To discover and utilize these intermediate domains, we propose an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM). IDM has two functions: 1) it generates multiple intermediate domains by mixing the hidden-layer features from source and target domains and 2) it dynamically reduces the domain gap between the source / target domain features and the intermediate domain features. While IDM achieves good domain alignment, it introduces a side effect, i.e., the mix-up operation may mix the identities into a new identity and lose the original identities. To compensate this, MGM is introduced by mapping the features into the IDM-generated intermediate domains without changing their original identity. It allows to focus on minimizing domain variations to promote the alignment between the source / target domain and intermediate domains, which reinforces IDM into IDM++. We extensively evaluate our method under both the UDA and domain generalization (DG) scenarios and observe that IDM++ yields consistent performance improvement for cross-domain re-ID, achieving new state of the art.

preprint2022arXiv

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

In this paper, we study the cluster head detection problem of a two-level unmanned aerial vehicle (UAV) swarm network (USNET) with multiple UAV clusters, where the inherent follow strategy (IFS) of low-level follower UAVs (FUAVs) with respect to high-level cluster head UAVs (HUAVs) is unknown. We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time. Then, to detect the HUAVs in the USNET with multiple UAV clusters, we develop a multi-cluster graph attention self-supervised learning algorithm (MC-GASSL) based on the GASSL. The MC-GASSL clusters the USNET with a gated recurrent unit (GRU)-based metric learning scheme and finds the HUAVs in each cluster with GASSL. Numerical results show that the GASSL can detect the HUAVs in single UAV clusters obeying various kinds of IFSs with over 98% average accuracy. The simulation results also show that the clustering purity of the USNET with MC-GASSL exceeds that with traditional clustering algorithms by at least 10% average. Furthermore, the MC-GASSL can efficiently detect all the HUAVs in USNETs with various IFSs and cluster numbers with low detection redundancies.

preprint2022arXiv

Data-Driven Learning of Safety-Critical Control with Stochastic Control Barrier Functions

Control barrier functions are widely used to synthesize safety-critical controls. The existence of Gaussian-type noise may lead to unsafe actions and result in severe consequences. While studies are widely done in safety-critical control for stochastic systems, in many real-world applications, we do not have the knowledge of the stochastic component of the dynamics. In this paper, we study safety-critical control of stochastic systems with an unknown diffusion part and propose a data-driven method to handle these scenarios. More specifically, we propose a data-driven stochastic control barrier function (DDSCBF) framework and use supervised learning to learn the unknown stochastic dynamics via the DDSCBF scheme. Under some reasonable assumptions, we provide guarantees that the DDSCBF scheme can approximate the Itô derivative of the stochastic control barrier function (SCBF) under partially unknown dynamics using the universal approximation theorem. We also show that we can achieve the same safety guarantee using the DDSCBF scheme as with SCBF in previous work without requiring the knowledge of stochastic dynamics. We use two non-linear stochastic systems to validate our theory in simulations.

preprint2022arXiv

Deterministic distribution of orbital angular momentum multiplexed continuous-variable entanglement and quantum steering

Orbital angular momentum (OAM) multiplexing provides an efficient method to improve data-carrying capacity in various quantum communication protocols. It is a precondition to distribute OAM multiplexed quantum resources in quantum channels for implementing quantum communication. However, quantum steering of OAM multiplexed optical fields and the effect of channel noise on OAM multiplexed quantum resources remain unclear. Here, we generate OAM multiplexed continuous-variable (CV) entangled states and distribute them in lossy or noisy channels. We show that the decoherence property of entanglement and quantum steering of the OAM multiplexed states carrying topological charges $l=1$ and $l=2$ are the same as that of the Gaussian mode with $l=0$ in lossy and noisy channels. The sudden death of entanglement and quantum steering of high-order OAM multiplexed states is observed in the presence of excess noise. Our results demonstrate the feasibility to realize high data-carrying capacity quantum information processing by utilizing OAM multiplexed CV entangled states.

preprint2022arXiv

Diffraction properties of lights with transverse orbital angular momentum

Spatiotemporal optical vortex (STOV) is a unique optical vortex with phase singularity in the space-time domain and the photons in a STOV can carry transverse orbital angular momentum (OAM). The STOV shows many fantastic properties which are worth exploring. Here, we theoretically and experimentally study the diffraction property of STOV, which is a fundamental wave phenomenon. The diffraction behaviors of STOVs are obviously affected by the transverse OAM. The diffraction patterns of STOV pulses diffracted by a grating show multi-lobe structure with each gap corresponding to 1 topological charge. The diffraction properties of lights with transverse OAM are demonstrated clearly and help us understanding the physical properties of STOV, which will be of special applications, such as the realization of fast detection of STOVs with different topological charges, which may pay the way for STOV based optical communication.

preprint2022arXiv

ERA: Expert Retrieval and Assembly for Early Action Prediction

Early action prediction aims to successfully predict the class label of an action before it is completely performed. This is a challenging task because the beginning stages of different actions can be very similar, with only minor subtle differences for discrimination. In this paper, we propose a novel Expert Retrieval and Assembly (ERA) module that retrieves and assembles a set of experts most specialized at using discriminative subtle differences, to distinguish an input sample from other highly similar samples. To encourage our model to effectively use subtle differences for early action prediction, we push experts to discriminate exclusively between samples that are highly similar, forcing these experts to learn to use subtle differences that exist between those samples. Additionally, we design an effective Expert Learning Rate Optimization method that balances the experts' optimization and leads to better performance. We evaluate our ERA module on four public action datasets and achieve state-of-the-art performance.

preprint2022arXiv

Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach

Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency synchronization significantly impacts the overall system performance. In this paper, we propose a novel scheme leveraging extreme learning machine (ELM) to achieve high-precision synchronization. Specifically, exploiting the preamble signals with synchronization offsets, two ELMs are incorporated into a traditional MIMO-OFDM system to estimate both the residual symbol timing offset (RSTO) and the residual carrier frequency offset (RCFO). The simulation results show that the performance of the proposed ELM-based synchronization scheme is superior to the traditional method under both additive white Gaussian noise (AWGN) and frequency selective fading channels. Furthermore, comparing with the existing machine learning based techniques, the proposed method shows outstanding performance without the requirement of perfect channel state information (CSI) and prohibitive computational complexity. Finally, the proposed method is robust in terms of the choice of channel parameters (e.g., number of paths) and also in terms of "generalization ability" from a machine learning standpoint.

preprint2022arXiv

GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation

Generating recommendations based on user-item interactions and user-user social relations is a common use case in web-based systems. These connections can be naturally represented as graph-structured data and thus utilizing graph neural networks (GNNs) for social recommendation has become a promising research direction. However, existing graph-based methods fails to consider the bias offsets of users (items). For example, a low rating from a fastidious user may not imply a negative attitude toward this item because the user tends to assign low ratings in common cases. Such statistics should be considered into the graph modeling procedure. While some past work considers the biases, we argue that these proposed methods only treat them as scalars and can not capture the complete bias information hidden in data. Besides, social connections between users should also be differentiable so that users with similar item preference would have more influence on each other. To this end, we propose Graph-Based Decentralized Collaborative Filtering for Social Recommendation (GDSRec). GDSRec treats the biases as vectors and fuses them into the process of learning user and item representations. The statistical bias offsets are captured by decentralized neighborhood aggregation while the social connection strength is defined according to the preference similarity and then incorporated into the model design. We conduct extensive experiments on two benchmark datasets to verify the effectiveness of the proposed model. Experimental results show that the proposed GDSRec achieves superior performance compared with state-of-the-art related baselines. Our implementations are available in \url{https://github.com/MEICRS/GDSRec}.

preprint2022arXiv

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection.

preprint2022arXiv

Human Action Recognition from Various Data Modalities: A Review

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this paper, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.

preprint2022arXiv

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for skeleton-based interaction recognition via modeling the interactive body parts as graphs. More specifically, the proposed IGFormer constructs interaction graphs according to the semantic and distance correlations between the interactive body parts, and enhances the representation of each person by aggregating the information of the interactive body parts based on the learned graphs. Furthermore, we propose a Semantic Partition Module to transform each human skeleton sequence into a Body-Part-Time sequence to better capture the spatial and temporal information of the skeleton sequence for learning the graphs. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art with a significant margin.

preprint2022arXiv

Image Segmentation with Adaptive Spatial Priors from Joint Registration

Image segmentation is a crucial but challenging task that has many applications. In medical imaging for instance, intensity inhomogeneity and noise are common. In thigh muscle images, different muscles are closed packed together and there are often no clear boundaries between them. Intensity based segmentation models cannot separate one muscle from another. To solve such problems, in this work we present a segmentation model with adaptive spatial priors from joint registration. This model combines segmentation and registration in a unified framework to leverage their positive mutual influence. The segmentation is based on a modified Gaussian mixture model (GMM), which integrates intensity inhomogeneity and spacial smoothness. The registration plays the role of providing a shape prior. We adopt a modified sum of squared difference (SSD) fidelity term and Tikhonov regularity term for registration, and also utilize Gaussian pyramid and parametric method for robustness. The connection between segmentation and registration is guaranteed by the cross entropy metric that aims to make the segmentation map (from segmentation) and deformed atlas (from registration) as similar as possible. This joint framework is implemented within a constraint optimization framework, which leads to an efficient algorithm. We evaluate our proposed model on synthetic and thigh muscle MR images. Numerical results show the improvement as compared to segmentation and registration performed separately and other joint models.

preprint2022arXiv

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

Machine reading comprehension has aroused wide concerns, since it explores the potential of model for text understanding. To further equip the machine with the reasoning capability, the challenging task of logical reasoning is proposed. Previous works on logical reasoning have proposed some strategies to extract the logical units from different aspects. However, there still remains a challenge to model the long distance dependency among the logical units. Also, it is demanding to uncover the logical structures of the text and further fuse the discrete logic to the continuous text embedding. To tackle the above issues, we propose an end-to-end model Logiformer which utilizes a two-branch graph transformer network for logical reasoning of text. Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively. The logical graph models the causal relations for the logical branch while the syntax graph captures the co-occurrence relations for the syntax branch. Secondly, to model the long distance dependency, the node sequence from each graph is fed into the fully connected graph transformer structures. The two adjacent matrices are viewed as the attention biases for the graph transformer layers, which map the discrete logical structures to the continuous text embedding space. Thirdly, a dynamic gate mechanism and a question-aware self-attention module are introduced before the answer prediction to update the features. The reasoning process provides the interpretability by employing the logical units, which are consistent with human cognition. The experimental results show the superiority of our model, which outperforms the state-of-the-art single model on two logical reasoning benchmarks.

preprint2022arXiv

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video. However, due to the long-tailed training data in datasets, the generalization performance of existing VidSGG models can be affected by the spatio-temporal conditional bias problem. In this work, from the perspective of meta-learning, we propose a novel Meta Video Scene Graph Generation (MVSGG) framework to address such a bias problem. Specifically, to handle various types of spatio-temporal conditional biases, our framework first constructs a support set and a group of query sets from the training data, where the data distribution of each query set is different from that of the support set w.r.t. a type of conditional bias. Then, by performing a novel meta training and testing process to optimize the model to obtain good testing performance on these query sets after training on the support set, our framework can effectively guide the model to learn to well generalize against biases. Extensive experiments demonstrate the efficacy of our proposed framework.

preprint2022arXiv

Multiple Control Barrier Functions: An Application to Reactive Obstacle Avoidance for a Multi-steering Tractor-trailer System

Control barrier functions (CBFs) recently introduced a systematic way to guarantee the system's safety through set invariance. Together with a nominal control method, it establishes a safety-critical control mechanism. The resulting safety constraints can be enforced as hard constraints in quadratic programming (QP) optimization, which rectifies the nominal control law based on the set of safe inputs. In this work, we introduce a multiple CBFs scheme which enforces several safety constraints with high relative degrees. This control structure is essential in many challenging robotic applications that need to meet several safety criteria simultaneously. In order to illustrate the capabilities of the proposed method, we have addressed the problem of reactive obstacle avoidance for a class of tractor-trailer systems. Safety is one of the fundamental issues in autonomous tractor-trailer systems design. The lack of fast response due to poor maneuverability makes reactive obstacle avoidance difficult for these systems. We develop a control structure based on a multiple CBFs scheme for a multi-steering tractor-trailer system to ensure a collision-free maneuver for both the tractor and trailer in the presence of several obstacles. Model predictive control is selected as the nominal tracking controller, and the proposed control strategy is tested in several challenging scenarios.

preprint2022arXiv

Multistage smoothing based multistep pulse compressor for ultrahigh peak power lasers

Ultrahigh peak power lasers are important scientific tools for frontier laser-physics researches, in which both the peak power improvement and operating safety are very important meanwhile limited by the damage threshold and size of compression gratings currently. Based on a recent reported method "multistep pulse compressor (MPC)", a multistage smoothing based MPC (MS-MPC) is proposed here to further improve the running safety, operating convenience, and simplify the whole setup of the MPC. In this optimized design, the beam smoothing is not simply executed in the pre-compressor or main-compressor, but separated into multistage. Then, it can protect important optics in every stage directly and reduce the executing difficult of typical MPC at the same time. The prism pair based pre-compressor will induce suitable spatial dispersion which is easier to be achieved and enough to protect the first grating directly. At the same time, the asymmetric four-grating compressor (AFGC) will also induce spatial dispersion to further smooth the laser beam which helps to protect the last grating directly. In this way, 10s-100s PW lasers can be compressed by using current available optics with improved operating safety owing to remove random spatial intensity modulations. Furthermore, an additional beam smoothing stage can be added before the main amplifier to protect the biggest amplification crystal away from damage. This MS-MPC optical design can be easily extended to be used in all exist PW laser facilities to improve their potential compressed pulse energy and running safety.

preprint2022arXiv

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

preprint2022arXiv

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills. This very challenging task has generated a lot of interest in recent years, with new solutions appearing rapidly. In this paper, we propose a nVFNet-RDC approach for continual object detection. Our nVFNet-RDC consists of teacher-student models, and adopts replay and feature distillation strategies. As the 1st place solutions, we achieve 55.94% and 54.65% average mAP on the 3rd CLVision Challenge Track 2 and Track 3, respectively.

preprint2022arXiv

Observation of short-period helical spin order and magnetic transition in a non-chiral centrosymmetric helimagnet

The search for materials exhibiting nanoscale spiral order continues to be fuelled by the promise of emergent inductors. Although such spin textures have been reported in many materials, most of them exhibit long periods or are limited to operate far below room temperature. Here, we present the real-space observation of an ordered helical spin order with a period of 3.2 nm in a non-chiral centrosymmetric helimagnet MnCoSi at room temperature via multi-angle and multi-azimuth approach of Lorentz transmission electron microscopy (TEM). A magnetic transition from the ordered helical spin order to a cycloidal spin order below 228 K is clearly revealed by in situ neutron powder diffraction and Lorentz TEM, which is closely correlated with temperature-induced variation in magneto-crystalline anisotropy. These results reveal the origin of spiral ordered spin textures in non-chiral centrosymmetric helimagnet, which can serve as a new strategy for searching materials with nanoscale spin order with potential applications in emergent electromagnetism.

preprint2022arXiv

On Almost Sure Convergence Rates of Stochastic Gradient Methods

The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergence is clearly important to ensure that any instantiation of the stochastic algorithms would converge with probability one. Here we provide a unified almost sure convergence rates analysis for stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods. We show, for the first time, that the almost sure convergence rates obtained for these stochastic gradient methods on strongly convex functions, are arbitrarily close to their optimal convergence rates possible. For non-convex objective functions, we not only show that a weighted average of the squared gradient norms converges to zero almost surely, but also the last iterates of the algorithms. We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.

preprint2022arXiv

Opening the Black Box of Deep Neural Networks in Physical Layer Communication

Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems. However, most studies in the physical layer have tended to focus on the application of DNN models to wireless communication problems but not to theoretically understand how does a DNN work in a communication system. In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques and their cost in terms of computational complexity. We further investigate and also experimentally validate how information is flown in a DNN-based communication system under the information theoretic concepts.

preprint2022arXiv

Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation

The morphological changes in knee cartilage (especially femoral and tibial cartilages) are closely related to the progression of knee osteoarthritis, which is expressed by magnetic resonance (MR) images and assessed on the cartilage segmentation results. Thus, it is necessary to propose an effective automatic cartilage segmentation model for longitudinal research on osteoarthritis. In this research, to relieve the problem of inaccurate discontinuous segmentation caused by the limited receptive field in convolutional neural networks, we proposed a novel position-prior clustering-based self-attention module (PCAM). In PCAM, long-range dependency between each class center and feature point is captured by self-attention allowing contextual information re-allocated to strengthen the relative features and ensure the continuity of segmentation result. The clutsering-based method is used to estimate class centers, which fosters intra-class consistency and further improves the accuracy of segmentation results. The position-prior excludes the false positives from side-output and makes center estimation more precise. Sufficient experiments are conducted on OAI-ZIB dataset. The experimental results show that the segmentation performance of combination of segmentation network and PCAM obtains an evident improvement compared to original model, which proves the potential application of PCAM in medical segmentation tasks. The source code is publicly available from link: https://github.com/LeongDong/PCAMNet

preprint2022arXiv

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

Objectives: To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN. Methods: A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model. Results: The best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density ($p$ = 0.015), circumference ($p$ = 0.009), circularity ($p$ = 0.010), and orientation ($p$ = 0.012). Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC. The codes and dataset are available at https://github.com/bupt-ai-cz/BALNMP

preprint2022arXiv

Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking

The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging. Firstly, the states need to be able to represent compound entities such as symptoms with their body part or diseases with degrees of severity to provide enough information for decision support. Secondly, these named entities in the utterance might be discontinuous and scattered across sentences and speakers. These also make it difficult to annotate a large corpus which is essential for most methods. Therefore, we first define a multi-hierarchical state structure. We annotate and publish a medical dialogue dataset in Chinese. To the best of our knowledge, there are no publicly available ones before. Then we propose a Prompt-based Generative Approach which can generate slot values with multi-hierarchies incrementally using a top-down approach. A dialogue style prompt is also supplemented to utilize the large unlabeled dialogue corpus to alleviate the data scarcity problem. The experiments show that our approach outperforms other DST methods and is rather effective in the scenario with little data.

preprint2022arXiv

Quantum coherence of an orbital angular momentum multiplexed continuous-variable entangled state

Orbital angular momentum (OAM) multiplexed entangled state is an important quantum resource for high dimensional quantum information processing. In this paper, we experimentally quantify quantum coherence of OAM multiplexed continuous-variable (CV) entangled state and characterize its evolution in a noisy environment. We show that the quantum coherence of the OAM multiplexed CV entangled state carrying topological charges $l=1$ and $l=2$ are the same as that of the Gaussian mode with $l=0$ in a noisy channel. Furthermore, we show that the quantum coherence of OAM multiplexed entangled state is robust to noise, even though the sudden death of entanglement is observed. Our results provide reference for applying quantum coherence of OAM multiplexed CV entangled state in a noisy environment.

preprint2022arXiv

Reactive Task and Motion Planning for Robust Whole-Body Dynamic Locomotion in Constrained Environments

Contact-based decision and planning methods are becoming increasingly important to endow higher levels of autonomy for legged robots. Formal synthesis methods derived from symbolic systems have great potential for reasoning about high-level locomotion decisions and achieving complex maneuvering behaviors with correctness guarantees. This study takes a first step toward formally devising an architecture composed of task planning and control of whole-body dynamic locomotion behaviors in constrained and dynamically changing environments. At the high level, we formulate a two-player temporal logic game between the multi-limb locomotion planner and its dynamic environment to synthesize a winning strategy that delivers symbolic locomotion actions. These locomotion actions satisfy the desired high-level task specifications expressed in a fragment of temporal logic. Those actions are sent to a robust finite transition system that synthesizes a locomotion controller that fulfills state reachability constraints. This controller is further executed via a low-level motion planner that generates feasible locomotion trajectories. We construct a set of dynamic locomotion models for legged robots to serve as a template library for handling diverse environmental events. We devise a replanning strategy that takes into consideration sudden environmental changes or large state disturbances to increase the robustness of the resulting locomotion behaviors. We formally prove the correctness of the layered locomotion framework guaranteeing a robust implementation by the motion planning layer. Simulations of reactive locomotion behaviors in diverse environments indicate that our framework has the potential to serve as a theoretical foundation for intelligent locomotion behaviors.

preprint2022arXiv

Resolving the inner parsec of the blazar J1924-2914 with the Event Horizon Telescope

The blazar J1924-2914 is a primary Event Horizon Telescope (EHT) calibrator for the Galactic Center's black hole Sagittarius A*. Here we present the first total and linearly polarized intensity images of this source obtained with the unprecedented 20 $μ$as resolution of the EHT. J1924-2914 is a very compact flat-spectrum radio source with strong optical variability and polarization. In April 2017 the source was observed quasi-simultaneously with the EHT (April 5-11), the Global Millimeter VLBI Array (April 3), and the Very Long Baseline Array (April 28), giving a novel view of the source at four observing frequencies, 230, 86, 8.7, and 2.3 GHz. These observations probe jet properties from the subparsec to 100-parsec scales. We combine the multi-frequency images of J1924-2914 to study the source morphology. We find that the jet exhibits a characteristic bending, with a gradual clockwise rotation of the jet projected position angle of about 90 degrees between 2.3 and 230 GHz. Linearly polarized intensity images of J1924-2914 with the extremely fine resolution of the EHT provide evidence for ordered toroidal magnetic fields in the blazar compact core.

preprint2022arXiv

Robustly Complete Finite-State Abstractions for Verification of Stochastic Systems

In this paper, we focus on discrete-time stochastic systems modelled by nonlinear stochastic difference equations and propose robust abstractions for verifying probabilistic linear temporal specifications. The current literature focuses on developing sound abstraction techniques for stochastic dynamics without perturbations. However, soundness thus far has only been shown for preserving the satisfaction probability of certain types of temporal-logic specification. We present constructive finite-state abstractions for verifying probabilistic satisfaction of general ω-regular linear-time properties of more general nonlinear stochastic systems. Instead of imposing stability assumptions, we analyze the probabilistic properties from the topological view of metrizable space of probability measures. Such abstractions are both sound and approximately complete. That is, given a concrete discrete-time stochastic system and an arbitrarily small L1-perturbation of this system, there exists a family of finite-state Markov chains whose set of satisfaction probabilities contains that of the original system and meanwhile is contained by that of the slightly perturbed system. A direct consequence is that, given a probabilistic linear-time specification, initializing within the winning/losing region of the abstraction system can guarantee a satisfaction/dissatisfaction for the original system. We make an interesting observation that, unlike the deterministic case, point-mass (Dirac) perturbations cannot fulfill the purpose of robust completeness.

preprint2022arXiv

Smoothing analysis of two robust multigrid methods for elliptic optimal control problems

In this paper we study and compare two multigrid relaxation schemes with coarsening by two, three, and four for solving elliptic sparse optimal control problems with control constraints. First, we perform a detailed local Fourier analysis (LFA) of a well-known collective Jacobi relaxation (CJR) scheme, where the optimal smoothing factors are derived. This insightful analysis reveals that the optimal relaxation parameters depend on mesh size and regularization parameters, which was not investigated in literature. Second, we propose and analyze a new mass-based Braess-Sarazin relaxation (BSR) scheme, which is proven to provide smaller smoothing factors than the CJR scheme when $α\ge ch^4$ for a small constant $c$. Here $α$ is the regularization parameter and $h$ is the spatial mesh step size. These schemes are successfully extended to control-constrained cases through the semi-smooth Newton method. Coarsening by three or four with BSR is competitive with coarsening by two. Numerical examples are presented to validate our theoretical outcomes. The proposed inexact BSR (IBSR) scheme, where two preconditioned conjugate gradients iterations are applied to the Schur complement system, yields better computational efficiency than the CJR scheme.

preprint2022arXiv

Sufficient Conditions for Robust Probabilistic Reach-Avoid-Stay Specifications using Stochastic Lyapunov-Barrier Functions

Stability and safety are crucial in safety-critical control of dynamical systems. The reach-avoid-stay objectives for deterministic dynamical systems can be effectively handled by formal methods as well as Lyapunov methods with soundness and approximate completeness guarantees. However, for continuous-time stochastic dynamical systems, probabilistic reach-avoid-stay problems are viewed as challenging tasks. Motivated by the recent surge of applications in characterizing safety-critical properties using Lyapunov-barrier functions, we aim to provide a stochastic version for the probabilistic reach-avoid-stay problems in consideration of robustness. To this end, we first establish a connection between stochastic stability with safety constraints and reach-avoid-stay specifications. We then prove that stochastic Lyapunov-barrier functions provide sufficient conditions for the target objectives. We apply Lyapunovbarrier conditions in control synthesis for reach-avoid-stay specifications, and show its effectiveness in a case study.

preprint2022arXiv

Surface Representation for Point Clouds

Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present \textbf{RepSurf} (representative surfaces), a novel representation of point clouds to \textbf{explicitly} depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around \textbf{0.008M} number of parameters, \textbf{0.04G} FLOPs, and \textbf{1.12ms} inference time, our method achieves \textbf{94.7\%} (+0.5\%) on ModelNet40, and \textbf{84.6\%} (+1.8\%) on ScanObjectNN for classification, while \textbf{74.3\%} (+0.8\%) mIoU on S3DIS 6-fold, and \textbf{70.0\%} (+1.6\%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains \textbf{71.2\%} (+2.1\%) mAP$\mathit{_{25}}$, \textbf{54.8\%} (+2.0\%) mAP$\mathit{_{50}}$ on ScanNetV2, and \textbf{64.9\%} (+1.9\%) mAP$\mathit{_{25}}$, \textbf{47.7\%} (+2.5\%) mAP$\mathit{_{50}}$ on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at \url{https://github.com/hancyran/RepSurf}.

preprint2022arXiv

Theoretical Analysis of Deep Neural Networks in Physical Layer Communication

Recently, deep neural network (DNN)-based physical layer communication techniques have attracted considerable interest. Although their potential to enhance communication systems and superb performance have been validated by simulation experiments, little attention has been paid to the theoretical analysis. Specifically, most studies in the physical layer have tended to focus on the application of DNN models to wireless communication problems but not to theoretically understand how does a DNN work in a communication system. In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity. To achieve this goal, we first analyze the encoding performance of a DNN-based transmitter and compare it to a traditional one. And then, we theoretically analyze the performance of DNN-based estimator and compare it with traditional estimators. Third, we investigate and validate how information is flown in a DNN-based communication system under the information theoretic concepts. Our analysis develops a concise way to open the "black box" of DNNs in physical layer communication, which can be applied to support the design of DNN-based intelligent communication techniques and help to provide explainable performance assessment.

preprint2022arXiv

Topmetal-M: a novel pixel sensor for compact tracking applications

The Topmetal-M is a large area pixel sensor (18 mm * 23 mm) prototype fabricated in a new 130 nm high-resistivity CMOS process in 2019. It contains 400 rows * 512 columns square pixels with the pitch of 40 μm. In Topmetal-M, a novel charge collection method combing the Monolithic Active Pixel Sensor (MAPS) and the Topmetal sensor has been proposed for the first time. Both the ionized charge deposited by the particle in the sensor and along the track over the sensor can be collected. The in-pixel circuit mainly consists of a low-noise charge sensitive amplifier to establish the signal for the energy reconstruction, and a discriminator with a Time-to-Amplitude Converter (TAC) for the Time of Arrival (TOA) measurement. With this mechanism, the trajectory, particle hit position, energy and arrival time of the particle can be measured. The analog signal from each pixel is accessible through time-shared multiplexing over the entire pixel array. This paper will discuss the design and preliminary test results of the Topmetal-M sensor.

preprint2022arXiv

Uncertainty Modeling for Out-of-Distribution Generalization

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features and do not explicitly consider the uncertain statistics discrepancy caused by potential domain shifts during testing. In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training. Specifically, we hypothesize that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution. Hence, each feature statistic is no longer a deterministic value, but a probabilistic point with diverse distribution possibilities. With the uncertain feature statistics, the models can be trained to alleviate the domain perturbations and achieve better robustness against potential domain shifts. Our method can be readily integrated into networks without additional parameters. Extensive experiments demonstrate that our proposed method consistently improves the network generalization ability on multiple vision tasks, including image classification, semantic segmentation, and instance retrieval. The code can be available at https://github.com/lixiaotong97/DSU.

preprint2021arXiv

A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning

How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues -- weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works.

preprint2021arXiv

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. Our major finding is that after standard finetuning, the model forgets some of the important language generation skills acquired during large-scale pretraining. We demonstrate the forgetting phenomenon through a set of detailed behavior analysis from the perspectives of knowledge transfer, context sensitivity, and function space projection. As a preliminary attempt to alleviate the forgetting problem, we propose an intuitive finetuning strategy named "mix-review". We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent. Finally, we discuss interesting behavior of the resulting dialogue model and its implications.

preprint2021arXiv

Asymmetric four-grating compressor for ultrafast high power lasers

The peak power improvement and running safety of petawatt (PW) lasers are limited by laser-induced damage of optical components with limited sizes and damage thresholds. Diffraction gratings in pulse compressors have been the shortest stave of PW lasers up to now, as to manufacture a high quality meter-sized grating remains particularly challenging. Here, the asymmetric four-grating compressor (AFGC) with asymmetric configuration is proposed for PW lasers to increase the maximum bearable output pulse energy and running safety without neither additional optical component nor extra control in comparison to a traditional Treacy four-grating compressor (TFGC) with symmetric configuration. In AFGC, suitable spatial dispersion can be introduced in the output laser beam which is able to decrease the laser spatial intensity modulation (LSIM) of the output beam on the final grating. The introduced spatial dispersion can be automatically compensated at the focal plane by using the spatiotemporal focusing technique. Based on this simple AFGC design, not only the damage risk of the final grating can be reduced, but also the maximum output pulse energy can be improved by about 1.8 times theoretically. As an example, 100 PW output power can be achieved theoretically by using the AFGC with an input beam size of 550*700 mm2.

preprint2021arXiv

Beam smoothing based on prism pair for multistep pulse compressor in PW lasers

Ultra-short ultra-intense laser provides unprecedented experimental tools and extreme physical conditions to explore frontier secrets of nature. Recently, multistep pulse compressor (MPC) was proposed to break through the limitation of the size and damage threshold of the grating in the compressor during the realization of higher peak power laser. In the MPC methods, beam smoothing in the pre-compressor is a very important process. Here, beam smoothing based on prism pair were studied technically, in which both the spatial profiles and the spectral dispersive properties were analyzed in detail. The simulation results show clearly that the prism pair can effectively smooth the laser beam. Furthermore, the beam smoothing is much more efficiency with shorter separated distance if two prism pairs are arranged to induce spatial dispersion at one direction or two directions. The results of beam smoothing here will help the optimized optical designs in all PW laser systems to improve their output and running safety.

preprint2021arXiv

Connecting glass-forming ability of binary mixtures of soft particles to equilibrium melting temperatures

The glass-forming ability is an important material property for manufacturing glasses and understanding the long-standing glass transition problem. Because of the nonequilibrium nature, it is difficult to develop the theory for it. Here we report that the glass-forming ability of binary mixtures of soft particles is related to the equilibrium melting temperatures. Due to the distinction in particle size or stiffness, the two components in a mixture effectively feel different melting temperatures, leading to a melting temperature gap. By varying the particle size, stiffness, and composition over a wide range of pressures, we establish a comprehensive picture for the glass-forming ability, based on our finding of the direct link between the glass-forming ability and the melting temperature gap. Our study reveals and explains the pressure and interaction dependence of the glass-forming ability of model glass-formers, and suggests strategies to optimize the glass-forming ability via the manipulation of particle interactions.

preprint2021arXiv

Gaussian Curvature Filter on 3D Meshes

Minimizing the Gaussian curvature of meshes can play a fundamental role in 3D mesh processing. However, there is a lack of computationally efficient and robust Gaussian curvature optimization method. In this paper, we present a simple yet effective method that can efficiently reduce Gaussian curvature for 3D meshes. We first present the mathematical foundation of our method. Then, we introduce a simple and robust implicit Gaussian curvature optimization method named Gaussian Curvature Filter (GCF). GCF implicitly minimizes Gaussian curvature without the need to explicitly calculate the Gaussian curvature itself. GCF is highly efficient and this method can be used in a large range of applications that involve Gaussian curvature. We conduct extensive experiments to demonstrate that GCF significantly outperforms state-of-the-art methods in minimizing Gaussian curvature, and geometric feature preserving soothing on 3D meshes. GCF program is available at https://github.com/tangwenming/GCF-filter.

preprint2021arXiv

Interaction Relational Network for Mutual Action Recognition

Person-person mutual action recognition (also referred to as interaction recognition) is an important research branch of human activity analysis. Current solutions in the field -- mainly dominated by CNNs, GCNs and LSTMs -- often consist of complicated architectures and mechanisms to embed the relationships between the two persons on the architecture itself, to ensure the interaction patterns can be properly learned. Our main contribution with this work is by proposing a simpler yet very powerful architecture, named Interaction Relational Network, which utilizes minimal prior knowledge about the structure of the human body. We drive the network to identify by itself how to relate the body parts from the individuals interacting. In order to better represent the interaction, we define two different relationships, leading to specialized architectures and models for each. These multiple relationship models will then be fused into a single and special architecture, in order to leverage both streams of information for further enhancing the relational reasoning capability. Furthermore we define important structured pair-wise operations to extract meaningful extra information from each pair of joints -- distance and motion. Ultimately, with the coupling of an LSTM, our IRN is capable of paramount sequential relational reasoning. These important extensions we made to our network can also be valuable to other problems that require sophisticated relational reasoning. Our solution is able to achieve state-of-the-art performance on the traditional interaction recognition datasets SBU and UT, and also on the mutual actions from the large-scale dataset NTU RGB+D. Furthermore, it obtains competitive performance in the NTU RGB+D 120 dataset interactions subset.

preprint2021arXiv

Jamming in confined geometry: Criticality of the jamming transition and implications of structural relaxation in confined supercooled liquids

In marginally jammed solids confined by walls, we calculate the particle and ensemble averaged value of an order parameter, $\left<Ψ(r)\right>$, as a function of the distance to the wall, $r$. Being a microscopic indicator of structural disorder and particle mobility in solids, $Ψ$ is by definition the response of the mean square particle displacement to the increase of temperature in the harmonic approximation and can be directly calculated from the normal modes of vibration of the zero-temperature solids. We find that, in confined jammed solids, $\left<Ψ(r)\right>$ curves at different pressures can collapse onto the same master curve following a scaling function, indicating the criticality of the jamming transition. The scaling collapse suggests a diverging length scale and marginal instability at the jamming transition, which should be accessible to sophisticatedly designed experiments. Moreover, $\left<Ψ(r)\right>$ is found to be significantly suppressed when approaching the wall and anisotropic in directions perpendicular and parallel to the wall. This finding can be applied to understand the $r$-dependence and anisotropy of the structural relaxation in confined supercooled liquids, providing another example of understanding or predicting behaviors of supercooled liquids from the perspective of the zero-temperature amorphous solids.

preprint2021arXiv

Multichannel adaptive signal detection: Basic theory and literature review

Multichannel adaptive signal detection jointly uses the test and training data to form an adaptive detector, and then make a decision on whether a target exists or not. Remarkably, the resulting adaptive detectors usually possess the constant false alarm rate (CFAR) properties, and hence no additional CFAR processing is needed. Filtering is not needed as a processing procedure either, since the function of filtering is embedded in the adaptive detector. Moreover, adaptive detection usually exhibits better detection performance than the filtering-then-CFAR detection technique. Multichannel adaptive signal detection has been more than 30 years since the first multichannel adaptive detector was proposed by Kelly in 1986. However, there are fewer overview articles on this topic. In this paper we give a tutorial overview of multichannel adaptive signal detection, with emphasis on Gaussian background. We present the main deign criteria for adaptive detectors, investigate the relationship between adaptive detection and filtering-then-CFAR detection, relationship between adaptive detectors and adaptive filters, summarize typical adaptive detectors, show numerical examples, give comprehensive literature review, and discuss some possible further research tracks.

preprint2021arXiv

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-ray Images

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases. Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models. To address these challenges, Multiscale Attention Guided deep network with Soft Distance regularization (MAG-SD) is proposed to automatically classify COVID-19 from pneumonia CXR images. In MAG-SD, MA-Net is used to produce prediction vector and attention from multiscale feature maps. To improve the robustness of trained model and relieve the shortage of training data, attention guided augmentations along with a soft distance regularization are posed, which aims at generating meaningful augmentations and reduce noise. Our multiscale attention model achieves better classification performance on our pneumonia CXR image dataset. Plentiful experiments are proposed for MAG-SD which demonstrates its unique advantage in pneumonia classification over cutting-edge models. The code is available at https://github.com/JasonLeeGHub/MAG-SD.

preprint2021arXiv

Quadrupling the stored charge by extending the accessible density of states

Nanosized energy storage, energy-harvesting, and functional devices are the three key components for integrated self-power systems. Here, we report on nanoscale electrochemical devices with a nearly three-fold enhanced stored charge under the field effect. We demonstrated the field-effect transistor can not only work as a functional component in nanodevices but also serve as an amplifier for the nanosized energy storage blocks. This unusual increase in energy storage is attributed to having a wide range of accessible electronic density of states (EDOS), hence redox reactions are occurring within the nanowire and not being confined to the surface. Initial results with MoS2 suggest that this field effect modulated energy storage mechanism may also apply to many other redox-active materials. Our work demonstrates the novel application of the field-effect in energy storage devices as a universal strategy to improve ion diffusion and the surface-active ion concentration of the active material, which can greatly enhance the charge storage ability of nanoscale devices. The fabrication process of the field-effect energy storage device is also compatible with microtechnology and can be integrated into other microdevices and nanodevices.

preprint2021arXiv

Smooth Converse Lyapunov-Barrier Theorems for Asymptotic Stability with Safety Constraints and Reach-Avoid-Stay Specifications

Stability and safety are two important aspects in safety-critical control of dynamical systems. It has been a well established fact in control theory that stability properties can be characterized by Lyapunov functions. Reachability properties can also be naturally captured by Lyapunov functions for finite-time stability. Motivated by safety-critical control applications, such as in autonomous systems and robotics, there has been a recent surge of interests in characterizing safety properties using barrier functions. Lyapunov and barrier functions conditions, however, are sometimes viewed as competing objectives. In this paper, we provide a unified theoretical treatment of Lyapunov and barrier functions in terms of converse theorems for stability properties with safety guarantees and reach-avoid-stay type specifications. We show that if a system (modeled as a dynamical system with measurable perturbations) possesses a stability with safety property, then there exists a smooth Lyapunov function to certify such a property. This Lyapunov function is shown to be defined on the entire set of initial conditions from which solutions satisfy this property. A similar but slightly weaker statement is made for reach-avoid-stay specifications. We show by a simple example that the latter statement cannot be strengthened without additional assumptions. We further extend the results for systems with control inputs and prove existence of converse Lyapunov-barrier functions for reach-and-avoid specifications. While the converse Lyapunov-barrier theorems are not constructive, as with classical converse Lyapunov theorems, we believe that the unified necessary and sufficient conditions with a single Lyapunov-barrier function are of theoretical interest and can hopefully shed some light on computational approaches.

preprint2020arXiv

A Necessary Condition on Chain Reachable Robustness of Dynamical Systems

It is ``folklore'' that the solution to a set reachability problem for a dynamical system is only noncomputable because of non-robustness reasons. A robustness condition that can be imposed on a dynamical system is the requirement of the chain reachable set to equal the closure of the reachable set. We claim that this condition necessarily imposes strong conditions on the dynamical system. For instance, if the space is connected and compact and we are computing a chain reachable robust single valued function $f$ then $f$ cannot have an unstable fixed point or unstable periodic cycle.

preprint2020arXiv

A Sparse Learning Approach to the Detection of Multiple Noise-Like Jammers

In this paper, we address the problem of detecting multiple Noise-Like Jammers (NLJs) through a radar system equipped with an array of sensors. To this end, we develop an elegant and systematic framework wherein two architectures are devised to jointly detect an unknown number of NLJs and to estimate their respective angles of arrival. The followed approach relies on the likelihood ratio test in conjunction with a cyclic estimation procedure which incorporates at the design stage a sparsity promoting prior. As a matter of fact, the problem at hand owns an inherent sparse nature which is suitably exploited. This methodological choice is dictated by the fact that, from a mathematical point of view, classical maximum likelihood approach leads to intractable optimization problems (at least to the best of authors' knowledge) and, hence, a suboptimum approach represents a viable means to solve them. Performance analysis is conducted on simulated data and shows the effectiveness of the proposed architectures in drawing a reliable picture of the electromagnetic threats illuminating the radar system.

preprint2020arXiv

A Variational Image Segmentation Model based on Normalized Cut with Adaptive Similarity and Spatial Regularization

Image segmentation is a fundamental research topic in image processing and computer vision. In the last decades, researchers developed a large number of segmentation algorithms for various applications. Amongst these algorithms, the Normalized cut (Ncut) segmentation method is widely applied due to its good performance. The Ncut segmentation model is an optimization problem whose energy is defined on a specifically designed graph. Thus, the segmentation results of the existing Ncut method are largely dependent on a pre-constructed similarity measure on the graph since this measure is usually given empirically by users. This flaw will lead to some undesirable segmentation results. In this paper, we propose a Ncut-based segmentation algorithm by integrating an adaptive similarity measure and spatial regularization. The proposed model combines the Parzen-Rosenblatt window method, non-local weights entropy, Ncut energy, and regularizer of phase field in a variational framework. Our method can adaptively update the similarity measure function by estimating some parameters. This adaptive procedure enables the proposed algorithm finding a better similarity measure for classification than the Ncut method. We provide some mathematical interpretation of the proposed adaptive similarity from multi-viewpoints such as statistics and convex optimization. In addition, the regularizer of phase field can guarantee that the proposed algorithm has a robust performance in the presence of noise, and it can also rectify the similarity measure with a spatial priori. The well-posed theory such as the existence of the minimizer for the proposed model is given in the paper. Compared with some existing segmentation methods such as the traditional Ncut-based model and the classical Chan-Vese model, the numerical experiments show that our method can provide promising segmentation results.

preprint2020arXiv

An Empirical Evaluation of GDPR Compliance Violations in Android mHealth Apps

The purpose of the General Data Protection Regulation (GDPR) is to provide improved privacy protection. If an app controls personal data from users, it needs to be compliant with GDPR. However, GDPR lists general rules rather than exact step-by-step guidelines about how to develop an app that fulfills the requirements. Therefore, there may exist GDPR compliance violations in existing apps, which would pose severe privacy threats to app users. In this paper, we take mobile health applications (mHealth apps) as a peephole to examine the status quo of GDPR compliance in Android apps. We first propose an automated system, named \mytool, to bridge the semantic gap between the general rules of GDPR and the app implementations by identifying the data practices declared in the app privacy policy and the data relevant behaviors in the app code. Then, based on \mytool, we detect three kinds of GDPR compliance violations, including the incompleteness of privacy policy, the inconsistency of data collections, and the insecurity of data transmission. We perform an empirical evaluation of 796 mHealth apps. The results reveal that 189 (23.7\%) of them do not provide complete privacy policies. Moreover, 59 apps collect sensitive data through different measures, but 46 (77.9\%) of them contain at least one inconsistent collection behavior. Even worse, among the 59 apps, only 8 apps try to ensure the transmission security of collected data. However, all of them contain at least one encryption or SSL misuse. Our work exposes severe privacy issues to raise awareness of privacy protection for app users and developers.

preprint2020arXiv

Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation

Accurate segmentation of skin lesion from dermoscopic images is a crucial part of computer-aided diagnosis of melanoma. It is challenging due to the fact that dermoscopic images from different patients have non-negligible lesion variation, which causes difficulties in anatomical structure learning and consistent skin lesion delineation. In this paper, we propose a novel bi-directional dermoscopic feature learning (biDFL) framework to model the complex correlation between skin lesions and their informative context. By controlling feature information passing through two complementary directions, a substantially rich and discriminative feature representation is achieved. Specifically, we place biDFL module on the top of a CNN network to enhance high-level parsing performance. Furthermore, we propose a multi-scale consistent decision fusion (mCDF) that is capable of selectively focusing on the informative decisions generated from multiple classification layers. By analysis of the consistency of the decision at each position, mCDF automatically adjusts the reliability of decisions and thus allows a more insightful skin lesion delineation. The comprehensive experimental results show the effectiveness of the proposed method on skin lesion segmentation, achieving state-of-the-art performance consistently on two publicly available dermoscopic image databases.

preprint2020arXiv

Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide distribution to improve the performance of remote sensing image aircraft detection. Specifically, to increase the variability of synthetic data, we randomly set the parameters during rendering, such as the size of the instance and the class of background images. In order to make the synthetic images more realistic, we then refine the synthetic images at the pixel level using CycleGAN with real unlabeled images. We also fine-tune the model with a small amount of real data, to obtain a higher accuracy. Experiments on NWPU VHR-10, UCAS-AOD and DIOR datasets demonstrate that the proposed method can be applied for augmenting insufficient real data.

preprint2020arXiv

Composite Signalling for DFRC: Dedicated Probing Signal or Not?

Dual-functional radar-communication (DFRC) is a promising new solution to simultaneously probe the radar target and transmit information in wireless networks. In this paper, we study the joint optimization of transmit and receive beamforming for the DFRC system. Specifically, the signal to interference plus noise ratio (SINR) of the radar is maximized under the SINR constraints of the communication user (CU), which characterizes the optimal tradeoff between radar and communication. In addition to simply using the communication signal for target probing, we further consider to exploit dedicated probing signals to enhance the radar sensing performance. We commence by studying the single-CU scenario, where a closed-form solution to the beamforming design problem is provided. It is then proved that a dedicated radar probing signal is not needed. As a further step, we consider a more complicated multi-CU scenario, where the beamforming design is formulated as a non-convex quadratically constrained quadratic programming. The optimal solutions are obtained by applying semidefinite relaxation with guaranteed rank-1 property. It is shown that under the multi-CU scenario, the dedicated probing signal should be employed to improve the radar performance at the cost of implementing an additional interference cancellation at the CU. Finally, the numerical simulations are provided to verify the effectiveness of the proposed algorithm.

preprint2020arXiv

Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation

Convex Shapes (CS) are common priors for optic disc and cup segmentation in eye fundus images. It is important to design proper techniques to represent convex shapes. So far, it is still a problem to guarantee that the output objects from a Deep Neural Convolution Networks (DCNN) are convex shapes. In this work, we propose a technique which can be easily integrated into the commonly used DCNNs for image segmentation and guarantee that outputs are convex shapes. This method is flexible and it can handle multiple objects and allow some of the objects to be convex. Our method is based on the dual representation of the sigmoid activation function in DCNNs. In the dual space, the convex shape prior can be guaranteed by a simple quadratic constraint on a binary representation of the shapes. Moreover, our method can also integrate spatial regularization and some other shape prior using a soft thresholding dynamics (STD) method. The regularization can make the boundary curves of the segmentation objects to be simultaneously smooth and convex. We design a very stable active set projection algorithm to numerically solve our model. This algorithm can form a new plug-and-play DCNN layer called CS-STD whose outputs must be a nearly binary segmentation of convex objects. In the CS-STD block, the convexity information can be propagated to guide the DCNN in both forward and backward propagation during training and prediction process. As an application example, we apply the convexity prior layer to the retinal fundus images segmentation by taking the popular DeepLabV3+ as a backbone network. Experimental results on several public datasets show that our method is efficient and outperforms the classical DCNN segmentation methods.

preprint2020arXiv

Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning

Segmentation from renal pathological images is a key step in automatic analyzing the renal histological characteristics. However, the performance of models varies significantly in different types of stained datasets due to the appearance variations. In this paper, we design a robust and flexible model for cross-stained segmentation. It is a novel multi-level deep adversarial network architecture that consists of three sub-networks: (i) a segmentation network; (ii) a pair of multi-level mirrored discriminators for guiding the segmentation network to extract domain-invariant features; (iii) a shape discriminator that is utilized to further identify the output of the segmentation network and the ground truth. Experimental results on glomeruli segmentation from renal biopsy images indicate that our network is able to improve segmentation performance on target type of stained images and use unlabeled data to achieve similar accuracy to labeled data. In addition, this method can be easily applied to other tasks.

preprint2020arXiv

Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation

We use Deep Convolutional Neural Networks (DCNNs) for image segmentation problems. DCNNs can well extract the features from natural images. However, the classification functions in the existing network architecture of CNNs are simple and lack capabilities to handle important spatial information in a way that have been done for many well-known traditional variational models. Prior such as spatial regularity, volume prior and object shapes cannot be well handled by existing DCNNs. We propose a novel Soft Threshold Dynamics (STD) framework which can easily integrate many spatial priors of the classical variational models into the DCNNs for image segmentation. The novelty of our method is to interpret the softmax activation function as a dual variable in a variational problem, and thus many spatial priors can be imposed in the dual space. From this viewpoint, we can build a STD based framework which can enable the outputs of DCNNs to have many special priors such as spatial regularity, volume constraints and star-shape priori. The proposed method is a general mathematical framework and it can be applied to any semantic segmentation DCNNs. To show the efficiency and accuracy of our method, we applied it to the popular DeepLabV3+ image segmentation network, and the experiments results show that our method can work efficiently on data-driven image segmentation DCNNs.

preprint2020arXiv

Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia

The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has infected more than 1,436,000 people in more than 200 countries and territories as of April 9, 2020. Detecting COVID-19 at early stage is essential to deliver proper healthcare to the patients and also to protect the uninfected population. To this end, we develop a dual-sampling attention network to automatically diagnose COVID- 19 from the community acquired pneumonia (CAP) in chest computed tomography (CT). In particular, we propose a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses. Note that there exists imbalanced distribution of the sizes of the infection regions between COVID-19 and CAP, partially due to fast progress of COVID-19 after symptom onset. Therefore, we develop a dual-sampling strategy to mitigate the imbalanced learning. Our method is evaluated (to our best knowledge) upon the largest multi-center CT data for COVID-19 from 8 hospitals. In the training-validation stage, we collect 2186 CT scans from 1588 patients for a 5-fold cross-validation. In the testing stage, we employ another independent large-scale testing dataset including 2796 CT scans from 2057 patients. Results show that our algorithm can identify the COVID-19 images with the area under the receiver operating characteristic curve (AUC) value of 0.944, accuracy of 87.5%, sensitivity of 86.9%, specificity of 90.1%, and F1-score of 82.0%. With this performance, the proposed algorithm could potentially aid radiologists with COVID-19 diagnosis from CAP, especially in the early stage of the COVID-19 outbreak.

preprint2020arXiv

Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos

Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, important but challenging measurement problem. To solve this problem, we propose a new method superior to the traditional ways in two aspects, without preprocessing and applicable for arbitrary periodicity actions. Without preprocessing, the proposed model makes our method convenient for real applications; processing the arbitrary periodicity action makes our model more suitable for the actual circumstance. In terms of methodology, firstly, we analyze the movement patterns of the repetitive actions based on the spatial and temporal features of actions extracted by deep ConvNets; Secondly, the Principal Component Analysis algorithm is used to generate the intuitive periodic information from the chaotic high-dimensional deep features; Thirdly, the periodicity is mined based on the high-energy rule using Fourier transform; Finally, the inverse Fourier transform with a multi-stage threshold filter is proposed to improve the quality of the mined periodicity, and peak detection is introduced to finish the repetition counting. Our work features two-fold: 1) An important insight that deep features extracted for action recognition can well model the self-similarity periodicity of the repetitive action is presented. 2) A high-energy based periodicity mining rule using deep features is presented, which can process arbitrary actions without preprocessing. Experimental results show that our method achieves comparable results on the public datasets YT Segments and QUVA.

preprint2020arXiv

High-temperature and Abrasion Resistant Selective Solar Absorber under Ambient Environment

Selective solar absorbers (SSAs) with high performance are the key to concentrated solar power systems. Optical metamaterials are emerging as a promising strategy to enhance selective photon absorption, however, the high-temperature resistance (>500C) remains as one of the main challenges for their practical applications. Here, a multilayered metamaterial system (Al2O3/W/SiO2/W) based on metal-insulator-metal (MIM) resonance effect has been demonstrated with high solar absorptance over 92%, low thermal emittance loss below 6%, and significant high-temperature resistance: it has been proved that the optical performance remains 93.6% after 1-hour thermal annealing under ambient environment up to 500C, and 94.1% after 96-hour thermal cycle test at 400C, which is also confirmed by the microscopic morphology characterization. The spectral selectivity of fabricated SSAs is angular independent and polarization insensitive. Outdoor tests demonstrate that a peak temperature rise (193.5C) can be achieved with unconcentrated solar irradiance and surface abrasion resistance test yields that SSAs have a robust resistance to abrasion attack for engineering applications.

preprint2020arXiv

HLO: Half-kernel Laplacian Operator for Surface Smoothing

This paper presents a simple yet effective method for feature-preserving surface smoothing. Through analyzing the differential property of surfaces, we show that the conventional discrete Laplacian operator with uniform weights is not applicable to feature points at which the surface is non-differentiable and the second order derivatives do not exist. To overcome this difficulty, we propose a Half-kernel Laplacian Operator (HLO) as an alternative to the conventional Laplacian. Given a vertex v, HLO first finds all pairs of its neighboring vertices and divides each pair into two subsets (called half windows); then computes the uniform Laplacians of all such subsets and subsequently projects the computed Laplacians to the full-window uniform Laplacian to alleviate flipping and degeneration. The half window with least regularization energy is then chosen for v. We develop an iterative approach to apply HLO for surface denoising. Our method is conceptually simple and easy to use because it has a single parameter, i.e., the number of iterations for updating vertices. We show that our method can preserve features better than the popular uniform Laplacian-based denoising and it significantly alleviates the shrinkage artifact. Extensive experimental results demonstrate that HLO is better than or comparable to state-of-the-art techniques both qualitatively and quantitatively and that it is particularly good at handling meshes with high noise. We will make our source code publicly available.

preprint2020arXiv

Improving probability selecting based weights for Satisfiability Problem

The Boolean Satisfiability problem (SAT) is important on artificial intelligence community and the impact of its solving on complex problems. Recently, great breakthroughs have been made respectively on stochastic local search (SLS) algorithms for uniform random k-SAT resulting in several state-of-the-art SLS algorithms Score2SAT, YalSAT, ProbSAT, CScoreSAT and on a hybrid algorithm for hard random SAT (HRS) resulting in one state-of-the-art hybrid algorithm SparrowToRiss. However, there is no an algorithm which can effectively solve both uniform random k-SAT and HRS. In this paper, we present a new SLS algorithm named SelectNTS for uniform random k-SAT and HRS. SelectNTS is an improved probability selecting based local search algorithm for SAT problem. The core of SelectNTS relies on new clause and variable selection heuristics. The new clause selection heuristic uses a new clause weighting scheme and a biased random walk. The new variable selection heuristic uses a probability selecting strategy with the variation of CC strategy based on a new variable weighting scheme. Extensive experimental results on the well-known random benchmarks instances from the SAT Competitions in 2017 and 2018, and on randomly generated problems, show that our algorithm outperforms state-of-the-art random SAT algorithms, and our SelectNTS can effectively solve both uniform random k-SAT and HRS.

preprint2020arXiv

In-house beam-splitting pulse compressor with compensated spatiotemporal coupling for high-energy petawatt lasers

One of the most serious bottleneck on achieving kilojoule-level high-energy petawatt (PW) to hundreds-petawatt (100PW) lasers with ps to fs pulse duration is the requirement of as large as meter-sized gratings in the compressor so as to avoid the laser-induced damage to the gratings. However, this kind of meter-sized grating with high quality is hard to manufacture so far. Here, we propose a new in-house beam-splitting compressor based on the property that the damage threshold of gratings depend on the pulse duration. The new scheme will simultaneously improve the stability, save expensive gratings, and simplify the size of compressor because the split beams share the first two parallel gratings. Furthermore, based on the fact that the transmitted wavefront of a glass plate can be much better and more precisely controlled than that of the diffraction wavefront of a large grating, then glass plates with designed transmitted wavefront are proposed to compensate the wavefront distortion introduced by the second, the third gratings, and other optics in-house such as the beam splitter. This simple and economical method can compensate the space-time distortion in the compressor and then improve the focal intensity, which otherwise cannot be compensated by the deformable mirror outside the compressor due to angular chirp. Together with multi-beams tiled-aperture combining scheme, the novel compressor provides a new scheme to achieve high-energy PW-100PW lasers or even exawatt lasers with relatively small gratings in the future.

preprint2020arXiv

Instant single-pixel imaging: on-chip real-time implementation based on instant ghost imaging algorithm

Single-pixel imaging (SPI) uses a single-pixel detector to create an image of an object. SPI relies on a computer to construct an image, thus increasing both the size and cost of SPI and limiting its application. We developed instant single-pixel imaging (ISPI), an on-chip SPI system that implements real-time imaging at a rate of 25 fps. ISPI uses the instant ghost imaging algorithm we proposed which leverages signal differences for image creation. It does not require a computer, which greatly reduces its cost and size. The reconstruct time of ISPI for image creation is almost zero because little processing is required after signal detection. ISPI paves the way for the practical application of SPI.

preprint2020arXiv

Knowledge forest: a novel model to organize knowledge fragments

With the rapid growth of knowledge, it shows a steady trend of knowledge fragmentization. Knowledge fragmentization manifests as that the knowledge related to a specific topic in a course is scattered in isolated and autonomous knowledge sources. We term the knowledge of a facet in a specific topic as a knowledge fragment. The problem of knowledge fragmentization brings two challenges: First, knowledge is scattered in various knowledge sources, which exerts users' considerable efforts to search for the knowledge of their interested topics, thereby leading to information overload. Second, learning dependencies which refer to the precedence relationships between topics in the learning process are concealed by the isolation and autonomy of knowledge sources, thus causing learning disorientation. To solve the knowledge fragmentization problem, we propose a novel knowledge organization model, knowledge forest, which consists of facet trees and learning dependencies. Facet trees can organize knowledge fragments with facet hyponymy to alleviate information overload. Learning dependencies can organize disordered topics to cope with learning disorientation. We conduct extensive experiments on three manually constructed datasets from the Data Structure, Data Mining, and Computer Network courses, and the experimental results show that knowledge forest can effectively organize knowledge fragments, and alleviate information overload and learning disorientation.

preprint2020arXiv

MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation

Predicting depth from a single image is an attractive research topic since it provides one more dimension of information to enable machines to better perceive the world. Recently, deep learning has emerged as an effective approach to monocular depth estimation. As obtaining labeled data is costly, there is a recent trend to move from supervised learning to unsupervised learning to obtain monocular depth. However, most unsupervised learning methods capable of achieving high depth prediction accuracy will require a deep network architecture which will be too heavy and complex to run on embedded devices with limited storage and memory spaces. To address this issue, we propose a new powerful network with a recurrent module to achieve the capability of a deep network while at the same time maintaining an extremely lightweight size for real-time high performance unsupervised monocular depth prediction from video sequences. Besides, a novel efficient upsample block is proposed to fuse the features from the associated encoder layer and recover the spatial size of features with the small number of model parameters. We validate the effectiveness of our approach via extensive experiments on the KITTI dataset. Our new model can run at a speed of about 110 frames per second (fps) on a single GPU, 37 fps on a single CPU, and 2 fps on a Raspberry Pi 3. Moreover, it achieves higher depth accuracy with nearly 33 times fewer model parameters than state-of-the-art models. To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices.

preprint2020arXiv

Molecular Characterizations of Variable Anisotropic Hardy Spaces with Applications to Boundedness of Calderón-Zygmund Operators

Let $p(\cdot):\ \mathbb{R}^n\to(0,\infty]$ be a variable exponent function satisfying the globally log-Hölder continuous condition and $A$ a general expansive matrix on $\mathbb{R}^n$. Let $H_A^{p(\cdot)}(\mathbb{R}^n)$ be the variable anisotropic Hardy space associated with $A$ defined via the non-tangential grand maximal function. In this article, via the known atomic characterization of $H_A^{p(\cdot)}(\mathbb{R}^n)$, the author establishes its molecular characterization with the known best possible decay of molecules. As an application, the author obtains a criterion on the boundedness of linear operators on $H_A^{p(\cdot)}(\mathbb{R}^n)$, which is used to prove the boundedness of anisotropic Calderón-Zygmund operators on $H_A^{p(\cdot)}(\mathbb{R}^n)$. In addition, the boundedness of anisotropic Calderón-Zygmund operators from $H_A^{p(\cdot)}(\mathbb{R}^n)$ to the variable Lebesgue space $L^{p(\cdot)}(\mathbb{R}^n)$ is also presented. All these results are new even in the classical isotropic setting.

preprint2020arXiv

Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet

The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate. In this paper, we propose a highly efficient multi-level malignant tissue detection through the designed adversarial CAC-UNet. A patch-level model with a pre-prediction strategy and a malignancy area guided label smoothing is adopted to remove the negative WSIs, with which to lower the risk of false positive detection. For the selected key patches by multi-model ensemble, an adversarial context-aware and appearance consistency UNet (CAC-UNet) is designed to achieve robust segmentation. In CAC-UNet, mirror designed discriminators are able to seamlessly fuse the whole feature maps of the skillfully designed powerful backbone network without any information loss. Besides, a mask prior is further added to guide the accurate segmentation mask prediction through an extra mask-domain discriminator. The proposed scheme achieves the best results in MICCAI DigestPath2019 challenge on colonoscopy tissue segmentation and classification task. The full implementation details and the trained models are available at https://github.com/Raykoooo/CAC-UNet.

preprint2020arXiv

On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts

A basic simulation-based reinforcement learning algorithm is the Monte Carlo Exploring States (MCES) method, also known as optimistic policy iteration, in which the value function is approximated by simulated returns and a greedy policy is selected at each iteration. The convergence of this algorithm in the general setting has been an open question. In this paper, we investigate the convergence of this algorithm for the case with undiscounted costs, also known as the stochastic shortest path problem. The results complement existing partial results on this topic and thereby helps further settle the open problem. As a side result, we also provide a proof of a version of the supermartingale convergence theorem commonly used in stochastic approximation.

preprint2020arXiv

Optimal allocation of face masks during the COVID-19 pandemic: a case study of the first epidemic wave in the United States

In this paper, we propose a two-group SIR epidemic model to simulate the outcome of stay-at-home policy and wearing face masks during the first COVID-19 epidemic wave in the United States. Based on our proposed model, we further use the optimal control approach (with the objective of minimizing total deaths) to find the optimal dynamical distribution of face masks between the healthcare workers and the general public. It is not surprising that all the face masks should be solely reserved for the healthcare workers if the supply is short. However, when the supply is indeed sufficient, our numerical study indicates that the general public should share a large portion of face masks at the beginning of an epidemic wave to dramatically reduce the death toll. This interesting result partially contradicts with the guideline advised by the US Surgeon General and the Centers for Disease Control and Prevention (CDC) in March 2020. The optimality of this sounding CDC guideline highly depends on the supply level of face masks that changes frequently, and hence it should be adjusted according to the supply of face masks.

preprint2020arXiv

Robustly Complete Synthesis of Memoryless Controllers for Nonlinear Systems with Reach-and-Stay Specifications

This paper proposes a finitely terminating algorithm to solve reach-and-stay control problems for nonlinear systems. The algorithm is guaranteed to return a control strategy if the specification is robustly realizable. Such a feature is desirable as the commonly used abstraction-based methods are sound but not complete for systems that are not incrementally stable. Fundamental to the proposed method is a fixed-point characterization of the winning set of the system with respect to a given specification, i.e., the initial states that can be controlled to satisfy the specification. The use of an adaptive partitioning scheme not only guarantees the approximation precision of the winning set but also reduces computational time. The effectiveness and efficiency are illustrated by several benchmarking examples.

preprint2020arXiv

Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images

Background: Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of affected patients increase rapidly, manual severity assessment becomes a labor-intensive task, and may lead to delayed treatment. Purpose: Using machine learning method to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images, and to explore the severity-related features from the resulting assessment model. Materials and Method: Chest CT images of 176 patients (age 45.3$\pm$16.5 years, 96 male and 80 female) with confirmed COVID-19 are used, from which 63 quantitative features, e.g., the infection volume/ratio of the whole lung and the volume of ground-glass opacity (GGO) regions, are calculated. A random forest (RF) model is trained to assess the severity (non-severe or severe) based on quantitative features. Importance of each quantitative feature, which reflects the correlation to the severity of COVID-19, is calculated from the RF model. Results: Using three-fold cross validation, the RF model shows promising results, i.e., 0.933 of true positive rate, 0.745 of true negative rate, 0.875 of accuracy, and 0.91 of area under receiver operating characteristic curve (AUC). The resulting importance of quantitative features shows that the volume and its ratio (with respect to the whole lung volume) of ground glass opacity (GGO) regions are highly related to the severity of COVID-19, and the quantitative features calculated from the right lung are more related to the severity assessment than those of the left lung. Conclusion: The RF based model can achieve automatic severity assessment (non-severe or severe) of COVID-19 infection, and the performance is promising. Several quantitative features, which have the potential to reflect the severity of COVID-19, were revealed.

preprint2020arXiv

Surface Superconductivity in the type II Weyl Semimetal TaIrTe4

The search for unconventional superconductivity in Weyl semimetal materials is currently an exciting pursuit, since such superconducting phases could potentially be topologically nontrivial and host exotic Majorana modes. The layered material TaIrTe4 is a newly predicted time-reversal invariant type II Weyl semimetal with minimum number of Weyl points. Here, we report the discovery of surface superconductivity in Weyl semimetal TaIrTe4. Our scanning tunneling microscopy/spectroscopy (STM/S) visualizes Fermi arc surface states of TaIrTe4 that are consistent with the previous angle-resolved photoemission spectroscopy (ARPES) results. By a systematic study based on STS at ultralow temperature, we observe uniform superconducting gaps on the sample surface. The superconductivity is further confirmed by electrical transport measurements at ultralow temperature, with an onset transition temperature (Tc) up to 1.54 K being observed. The normalized upper critical field h*(T/Tc) behavior and the stability of the superconductivity against the ferromagnet indicate that the discovered superconductivity is unconventional with the p-wave pairing. The systematic STS, thickness and angular dependent transport measurements reveal that the detected superconductivity is quasi-one-dimensional (quasi-1D) and occurs in the surface states. The discovery of the surface superconductivity in TaIrTe4 provides a new novel platform to explore topological superconductivity and Majorana modes.

preprint2020arXiv

Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images

Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19) will help detect infections early and assess the disease progression. Especially, automated severity assessment of COVID-19 in CT images plays an essential role in identifying cases that are in great need of intensive clinical care. However, it is often challenging to accurately assess the severity of this disease in CT images, due to variable infection regions in the lungs, similar imaging biomarkers, and large inter-case variations. To this end, we propose a synergistic learning framework for automated severity assessment of COVID-19 in 3D CT images, by jointly performing lung lobe segmentation and multi-instance classification. Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice). A multi-task multi-instance deep network (called M$^2$UNet) is then developed to assess the severity of COVID-19 patients and also segment the lung lobe simultaneously. Our M$^2$UNet consists of a patch-level encoder, a segmentation sub-network for lung lobe segmentation, and a classification sub-network for severity assessment (with a unique hierarchical multi-instance learning strategy). Here, the context information provided by segmentation can be implicitly employed to improve the performance of severity assessment. Extensive experiments were performed on a real COVID-19 CT image dataset consisting of 666 chest CT images, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.

preprint2020arXiv

Towards Cognitive Routing based on Deep Reinforcement Learning

Routing is one of the key functions for stable operation of network infrastructure. Nowadays, the rapid growth of network traffic volume and changing of service requirements call for more intelligent routing methods than before. Towards this end, we propose a definition of cognitive routing and an implementation approach based on Deep Reinforcement Learning (DRL). To facilitate the research of DRL-based cognitive routing, we introduce a simulator named RL4Net for DRL-based routing algorithm development and simulation. Then, we design and implement a DDPG-based routing algorithm. The simulation results on an example network topology show that the DDPG-based routing algorithm achieves better performance than OSPF and random weight algorithms. It demonstrate the preliminary feasibility and potential advantage of cognitive routing for future network.

preprint2020arXiv

Training ASR models by Generation of Contextual Information

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research. In this paper, we conduct a large-scale study evaluating the effectiveness of weakly-supervised learning for speech recognition by using loosely related contextual information as a surrogate for ground-truth labels. For weakly supervised training, we use 50k hours of public English social media videos along with their respective titles and post text to train an encoder-decoder transformer model. Our best encoder-decoder models achieve an average of 20.8% WER reduction over a 1000 hours supervised baseline, and an average of 13.4% WER reduction when using only the weakly supervised encoder for CTC fine-tuning. Our results show that our setup for weak supervision improved both the encoder acoustic representations as well as the decoder language generation abilities.

preprint2020arXiv

TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing methods, our model focuses on modeling the motion dynamics with coupled spatio-temporal features, local-global spatial features and global temporal co-occurrence features of the previous pose sequence. Specifically, the coupled spatio-temporal features describe the spatial and temporal structure information hidden in the natural human motion sequence, which can be mined by covering the space and time dimensions of the input pose sequence with the convolutional filters. The local-global spatial features that encode different correlations of different joints of the human body (e.g. strong correlations between joints of one limb, weak correlations between joints of different limbs) are captured hierarchically by enlarging the receptive field layer by layer and residual connections from the lower layers to the deeper layers in our proposed convolutional network. And the global temporal co-occurrence features represent the co-occurrence relationship that different subsequences in a complex motion sequence are appeared simultaneously, which can be obtained automatically with our proposed TrajectoryNet by reorganizing the temporal information as the depth dimension of the input tensor. Finally, future poses are approximated based on the captured motion dynamics features. Extensive experiments show that our method achieves state-of-the-art performance on three challenging benchmarks (e.g. Human3.6M, G3D, and FNTU), which demonstrates the effectiveness of our proposed method. The code will be available if the paper is accepted.

preprint2020arXiv

Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning

Image segmentation with a volume constraint is an important prior for many real applications. In this work, we present a novel volume preserving image segmentation algorithm, which is based on the framework of entropic regularized optimal transport theory. The classical Total Variation (TV) regularizer and volume preserving are integrated into a regularized optimal transport model, and the volume and classification constraints can be regarded as two measures preserving constraints in the optimal transport problem. By studying the dual problem, we develop a simple and efficient dual algorithm for our model. Moreover, to be different from many variational based image segmentation algorithms, the proposed algorithm can be directly unrolled to a new Volume Preserving and TV regularized softmax (VPTV-softmax) layer for semantic segmentation in the popular Deep Convolution Neural Network (DCNN). The experiment results show that our proposed model is very competitive and can improve the performance of many semantic segmentation nets such as the popular U-net.

preprint2020arXiv

ZSTAD: Zero-Shot Temporal Activity Detection

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.

preprint2019arXiv

A Thermal Resistance Network Model for Heat Conduction of Amorphous Polymers

Thermal conductivities (TCs) of the vast majority of amorphous polymers are in a very narrow range, 0.1 $\sim$ 0.5 Wm$^{-1}$K$^{-1}$, although single polymer chains possess TC of orders-of-magnitude higher. Entanglement of polymer chains plays an important role in determining the TC of bulk polymers. We propose a thermal resistance network (TRN) model for TC in amorphous polymers taking into account the entanglement of molecular chains. Our model explains well the physical origin of universally low TC observed in amorphous polymers. The empirical formulae of pressure and temperature dependence of TC can be successfully reproduced from our model not only in solid polymers but also in polymer melts. We further quantitatively explain the anisotropic TC in oriented polymers.

preprint2019arXiv

Design of reversible low-field magnetocaloric effect at room temperature in hexagonal MnMX ferromagnets

Giant magnetocaloric effect is widely achieved in hexagonal MnMX-based (M = Co or Ni, X = Si or Ge) ferromagnets at their first-order magnetostructural transition. However, the thermal hysteresis and the low sensitivity of the magnetostructural transition to the magnetic field inevitably lead to a sizeable irreversibility of the low-field magnetocaloric effect. In this work, we show an alternative way to realize a reversible low-field magnetocaloric effect in MnMX-based alloys by taking advantage of the second-order phase transition. With introducing Cu into Co in MnCoGe alloy, the martensitic transition is stabilized at high temperature, while the Curie temperature of the orthorhombic phase is reduced to room temperature. As a result, a second-order magnetic transition with negligible thermal hysteresis and a large magnetization change can be observed, enabling a large reversible magnetocaloric effect. By both calorimetric and direct measurements, a reversible adiabatic temperature change of about 1 K is obtained under a field change of 0-1 T at 304 K, which is larger than that obtained in a first-order magnetostructural transition. To get a better insight into the origin of these experimental results, first-principles calculations are carried out to characterize the chemical bonds and the magnetic exchange interaction. Our work provides a new understanding of the MnCoGe alloy and indicates a feasible route to improve the reversibility of the low-field magnetocaloric effect in the MnMX system.

Jun Liu

Quick read

Decide how to stay connected

How to connect with this researcher

Open a focused conversation when the fit is right

See the researcher in context

Building this graph slice

98 published item(s)

Continuous-tone Simple Points: An $\ell_0$-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation

FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

FlashDecoding++: Faster Large Language Model Inference on GPUs

FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs

Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text

Modeling Uncertain Feature Representation for Domain Generalization

The grand picture behind Jensen&#39;s inequality

The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge

A Boundary Regression Model for Nested Named Entity Recognition

A Direct Parallel-in-Time Quasi-Boundary Value Method for Inverse Space-Dependent Source Problems

A Fast Algorithm for Robust Action Selection in Multi-Agent Systems

A Piecewise Learning Framework for Control of Unknown Nonlinear Systems with Stability Guarantees

A special cross-tie domain wall in helimagnet

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

A Vanka-type multigrid solver for complex-shifted Laplacian systems from diagonalization-based parallel-in-time algorithms

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

Data-Driven Learning of Safety-Critical Control with Stochastic Control Barrier Functions

Deterministic distribution of orbital angular momentum multiplexed continuous-variable entanglement and quantum steering

Diffraction properties of lights with transverse orbital angular momentum

ERA: Expert Retrieval and Assembly for Early Action Prediction

Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach

GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

Human Action Recognition from Various Data Modalities: A Review

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

Image Segmentation with Adaptive Spatial Priors from Joint Registration

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Multiple Control Barrier Functions: An Application to Reactive Obstacle Avoidance for a Multi-steering Tractor-trailer System

Multistage smoothing based multistep pulse compressor for ultrahigh peak power lasers

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

Observation of short-period helical spin order and magnetic transition in a non-chiral centrosymmetric helimagnet

On Almost Sure Convergence Rates of Stochastic Gradient Methods

Opening the Black Box of Deep Neural Networks in Physical Layer Communication

Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation

Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides

Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking

Quantum coherence of an orbital angular momentum multiplexed continuous-variable entangled state

Reactive Task and Motion Planning for Robust Whole-Body Dynamic Locomotion in Constrained Environments

Resolving the inner parsec of the blazar J1924-2914 with the Event Horizon Telescope

Robustly Complete Finite-State Abstractions for Verification of Stochastic Systems

Smoothing analysis of two robust multigrid methods for elliptic optimal control problems

Sufficient Conditions for Robust Probabilistic Reach-Avoid-Stay Specifications using Stochastic Lyapunov-Barrier Functions

Surface Representation for Point Clouds

Theoretical Analysis of Deep Neural Networks in Physical Layer Communication

Topmetal-M: a novel pixel sensor for compact tracking applications

Uncertainty Modeling for Out-of-Distribution Generalization

A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning

Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models

Asymmetric four-grating compressor for ultrafast high power lasers

Beam smoothing based on prism pair for multistep pulse compressor in PW lasers

Connecting glass-forming ability of binary mixtures of soft particles to equilibrium melting temperatures

Gaussian Curvature Filter on 3D Meshes

Interaction Relational Network for Mutual Action Recognition

Jamming in confined geometry: Criticality of the jamming transition and implications of structural relaxation in confined supercooled liquids

Multichannel adaptive signal detection: Basic theory and literature review

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-ray Images

Quadrupling the stored charge by extending the accessible density of states

Smooth Converse Lyapunov-Barrier Theorems for Asymptotic Stability with Safety Constraints and Reach-Avoid-Stay Specifications

A Necessary Condition on Chain Reachable Robustness of Dynamical Systems

A Sparse Learning Approach to the Detection of Multiple Noise-Like Jammers

A Variational Image Segmentation Model based on Normalized Cut with Adaptive Similarity and Spatial Regularization

An Empirical Evaluation of GDPR Compliance Violations in Android mHealth Apps

Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation

Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?

Composite Signalling for DFRC: Dedicated Probing Signal or Not?

Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation

The grand picture behind Jensen's inequality