BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Miao Zhang

Miao Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionArtificial IntelligenceMachine Learningcond-mat.mes-halleess.IVNetworking and Internet Architecturephysics.geo-phComputation and Languagecond-mat.mtrl-scicond-mat.softcs.CYDistributed, Parallel, and Cluster Computingeess.SPGraphicsInformation Theorymath.ITmath.OCMultimediaphysics.app-phphysics.chem-phphysics.comp-phphysics.optics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
24works
0followers
22topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

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

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

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.

Published work

24 published item(s)

preprint2026arXiv

CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting

Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robotic teleoperation. These applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous networks. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5$\sim$20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Earthquake Source Depth Determination using Single Station Waveforms and Deep Learning

In areas with limited station coverage, earthquake depth constraints are much less accurate than their latitude and longitude. Traditional travel-time-based location methods struggle to constrain depths due to imperfect station distribution and the strong trade-off between source depth and origin time. Identifying depth phases at regional distances is usually hindered by strong wave scattering, which is particularly challenging for low-magnitude events. Deep learning algorithms, capable of extracting various features from seismic waveforms, including phase arrivals, phase amplitudes, as well as phase frequency, offer promising constraints to earthquake depths. In this work, we propose a novel depth feature extraction network (named VGGDepth), which directly maps seismic waveforms to earthquake depth using three-component waveforms. The network structure is adapted from VGG16 in computer vision. It is designed to take single-station three-component waveforms as inputs and produce depths as outputs, achieving a direct mapping from waveforms to depths. Two scenarios are considered in our model development: (1) training and testing solely on the same seismic station, and (2) generalizing by training and testing on different seismic stations within a particular region. We demonstrate the efficacy of our methodology using seismic data from the 2016-2017 Central Apennines, Italy earthquake sequence. Results demonstrate that earthquake depths can be estimated from single stations with uncertainties of hundreds of meters. These uncertainties are further reduced by averaging results from multiple stations. Our method shows strong potential for earthquake depth determination, particularly for events recorded by single or sparsely distributed stations, such as historically instrumented earthquakes.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Identity-Robust Language Model Generation via Content Integrity Preservation

Large Language Model (LLM) outputs often vary across user sociodemographic attributes, leading to disparities in factual accuracy, utility, and safety, even for objective questions where demographic information is irrelevant. Unlike prior work on stereotypical or representational bias, this paper studies identity-dependent degradation of core response quality. We show empirically that such degradation arises from biased generation behavior, despite factual knowledge being robustly encoded across identities. Motivated by this mismatch, we propose a lightweight, training-free framework for identity-robust generation that selectively neutralizes non-critical identity information while preserving semantically essential attributes, thus maintaining output content integrity. Experiments across four benchmarks and 18 sociodemographic identities demonstrate an average 77% reduction in identity-dependent bias compared to vanilla prompting and a 45% reduction relative to prompt-based defenses. Our work addresses a critical gap in mitigating the impact of user identity cues in prompts on core generation quality.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answering

Visual Question Answering (VQA) requires models to reason over multimodal information, combining visual and textual data. With the development of continual learning, significant progress has been made in retaining knowledge and adapting to new information in the VQA domain. However, current methods often struggle with balancing knowledge retention, adaptation, and robust feature representation. To address these challenges, we propose a novel framework with adaptive memory allocation and global noise filtering called MacVQA for visual question answering. MacVQA fuses visual and question information while filtering noise to ensure robust representations, and employs prototype-based memory allocation to optimize feature quality and memory usage. These designs enable MacVQA to balance knowledge acquisition, retention, and compositional generalization in continual VQA learning. Experiments on ten continual VQA tasks show that MacVQA outperforms existing baselines, achieving 43.38% average accuracy and 2.32% average forgetting on standard tasks, and 42.53% average accuracy and 3.60% average forgetting on novel composition tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignment

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing methods may overlook the structural contextual information within each modality, making them vulnerable to interference from shallow features. To address these challenges, we propose MyGram, a modality-aware graph transformer with global distribution for multi-modal entity alignment. Specifically, we develop a modality diffusion learning module to capture deep structural contextual information within modalities and enable fine-grained multi-modal fusion. In addition, we introduce a Gram Loss that acts as a regularization constraint by minimizing the volume of a 4-dimensional parallelotope formed by multi-modal features, thereby achieving global distribution consistency across modalities. We conduct experiments on five public datasets. Results show that MyGram outperforms baseline models, achieving a maximum improvement of 4.8% in Hits@1 on FBDB15K, 9.9% on FBYG15K, and 4.3% on DBP15K.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these methods are often prone to reward hacking, wherein models exploit biases in imperfect reward functions rather than yielding genuine performance gains. In this work, we identify that normalization could lead to miscalibration and directly removing the prompt-level standard deviation term yields an optimal policy ascent direction that is linear in the advantage but still limits the separation of genuine signals from noise. To mitigate the above issues, we propose Super-Linear Advantage Shaping (SLAS) by revisiting the functional update from an information geometry perspective. By extending the Fisher-Rao information metric with advantage-dependent weighting, SLAS introduces a non-linear geometric structure that reshapes the local policy space. This design relaxes constraints along high-advantage directions to amplify informative updates, while tightening those in low-advantage regions to suppress illusory gradients. In addition, batch-level normalization is applied to stabilize training under varying reward scales. Extensive evaluations demonstrate that SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks. In particular, it yields faster training dynamics, improved out-of-domain performance on GenEval and UniGenBench++, and enhanced robustness to model scaling, while mitigating reward hacking and preserving semantic and compositional fidelity in generations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents

Rapid biodiversity loss underscore the urgency of effective monitoring, yet manual surveys remain resource-intensive. While on-device AI offers a scalable alternative, its performance in the wild is often challenged by environmental variability. Current methods rely heavily on cloud resource, which requires continuous uploading of field data for model retraining. This approach is unsuitable for remote deployments because it consumes limited power and network connectivity. To address these constraints, this research proposes a shift from model adaptation to knowledge adaptation. We introduce an architecture that separates visual perception from reasoning, combining a visual encoder with a dynamic knowledge base. We uses an explicit knowledge base to replace implicitly encoding expert knowledge into model parameters. This method also supports knowledge sustainability by preserving expert insights in a structured form. Through cross-disciplinary collaboration with biologists and Indigenous communities, this work advances ethical AI co-development, fostering responsible and culturally informed ecosystem management.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TBPLaS 2.0: a Tight-Binding Package for Large-scale Simulation

The common exact diagonalization-based techniques to solving tight-binding models suffer from O(N^2) and O(N^3) scaling with respect to model size in memory and CPU time, hindering their applications in large tight-binding models. On the contrary, the tight-binding propagation method (TBPM) can achieve linear scaling in both memory and CPU time, and is capable of handling large tight-binding models with billions of orbitals. In this paper, we introduce version 2.0 of TBPLaS, a package for large-scale simulation based on TBPM. This new version brings significant improvements with many new features. Existing Python/Cython modeling tools have been thoroughly optimized, and a compatible C++ implementation of the modeling tools is now available, offering efficiency enhancement of several orders. The solvers have been rewritten in C++ from scratch, with the efficiency enhanced by several times or even by an order of magnitude. The workflow of utilizing solvers has also been unified into a more comprehensive and consistent manner. New features include spin texture, Berry curvature and Chern number calculation, partial diagonalization for specific eigenvalues and eigenstates, analytical Hamiltonian, and GPU computing support. The documentation and tutorials have also been updated to the new version. In this paper, we discuss the revisions with respect to version 1.3 and demonstrate the new features. Benchmarks on modeling tools and solvers are also provided.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

Predicting river flow in places without streamflow records is challenging because basins respond differently to climate, terrain, vegetation, and soils. Traditional basin attributes describe some of these differences, but they cannot fully represent the complexity of natural environments. This study examines whether AlphaEarth Foundation embeddings, which are learned from large collections of satellite images rather than designed by experts, offer a more informative way to describe basin characteristics. These embeddings summarize patterns in vegetation, land surface properties, and long-term environmental dynamics. We find that models using them achieve higher accuracy when predicting flows in basins not used for training, suggesting that they capture key physical differences more effectively than traditional attributes. We further investigate how selecting appropriate donor basins influences prediction in ungauged regions. Similarity based on the embeddings helps identify basins with comparable environmental and hydrological behavior, improving performance, whereas adding many dissimilar basins can reduce accuracy. The results show that satellite-informed environmental representations can strengthen hydrological forecasting and support the development of models that adapt more easily to different landscapes.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity

Federated Learning (FL) enables training a global model without sharing the decentralized raw data stored on multiple devices to protect data privacy. Due to the diverse capacity of the devices, FL frameworks struggle to tackle the problems of straggler effects and outdated models. In addition, the data heterogeneity incurs severe accuracy degradation of the global model in the FL training process. To address aforementioned issues, we propose a hierarchical synchronous FL framework, i.e., FedHiSyn. FedHiSyn first clusters all available devices into a small number of categories based on their computing capacity. After a certain interval of local training, the models trained in different categories are simultaneously uploaded to a central server. Within a single category, the devices communicate the local updated model weights to each other based on a ring topology. As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects. Besides, the combination of the synchronous update of multiple categories and the device communication within a single category help address the data heterogeneity issue while achieving high accuracy. We evaluate the proposed framework based on MNIST, EMNIST, CIFAR10 and CIFAR100 datasets and diverse heterogeneous settings of devices. Experimental results show that FedHiSyn outperforms six baseline methods, e.g., FedAvg, SCAFFOLD, and FedAT, in terms of training accuracy and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Handling Data Heterogeneity with Generative Replay in Collaborative Learning for Medical Imaging

Collaborative learning, which enables collaborative and decentralized training of deep neural networks at multiple institutions in a privacy-preserving manner, is rapidly emerging as a valuable technique in healthcare applications. However, its distributed nature often leads to significant heterogeneity in data distributions across institutions. In this paper, we present a novel generative replay strategy to address the challenge of data heterogeneity in collaborative learning methods. Different from traditional methods that directly aggregating the model parameters, we leverage generative adversarial learning to aggregate the knowledge from all the local institutions. Specifically, instead of directly training a model for task performance, we develop a novel dual model architecture: a primary model learns the desired task, and an auxiliary "generative replay model" allows aggregating knowledge from the heterogenous clients. The auxiliary model is then broadcasted to the central sever, to regulate the training of primary model with an unbiased target distribution. Experimental results demonstrate the capability of the proposed method in handling heterogeneous data across institutions. On highly heterogeneous data partitions, our model achieves ~4.88% improvement in the prediction accuracy on a diabetic retinopathy classification dataset, and ~49.8% reduction of mean absolution value on a Bone Age prediction dataset, respectively, compared to the state-of-the art collaborative learning methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on few-shot semantic segmentation, which is still a largely unexplored field. A few recent advances are often restricted to single-class few-shot segmentation. In this paper, we first present a novel multi-way (class) encoding and decoding architecture which effectively fuses multi-scale query information and multi-class support information into one query-support embedding. Multi-class segmentation is directly decoded upon this embedding. For better feature fusion, a multi-level attention mechanism is proposed within the architecture, which includes the attention for support feature modulation and attention for multi-scale combination. Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image. Extensive experiments on standard benchmarks PASCAL-5i and COCO-20i show clear benefits of our method over the state of the art in few-shot segmentation

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Segmenting across places: The need for fair transfer learning with satellite imagery

The increasing availability of high-resolution satellite imagery has enabled the use of machine learning to support land-cover measurement and inform policy-making. However, labelling satellite images is expensive and is available for only some locations. This prompts the use of transfer learning to adapt models from data-rich locations to others. Given the potential for high-impact applications of satellite imagery across geographies, a systematic assessment of transfer learning implications is warranted. In this work, we consider the task of land-cover segmentation and study the fairness implications of transferring models across locations. We leverage a large satellite image segmentation benchmark with 5987 images from 18 districts (9 urban and 9 rural). Via fairness metrics we quantify disparities in model performance along two axes -- across urban-rural locations and across land-cover classes. Findings show that state-of-the-art models have better overall accuracy in rural areas compared to urban areas, through unsupervised domain adaptation methods transfer learning better to urban versus rural areas and enlarge fairness gaps. In analysis of reasons for these findings, we show that raw satellite images are overall more dissimilar between source and target districts for rural than for urban locations. This work highlights the need to conduct fairness analysis for satellite imagery segmentation models and motivates the development of methods for fair transfer learning in order not to introduce disparities between places, particularly urban and rural locations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging

Federated learning is an emerging research paradigm for enabling collaboratively training deep learning models without sharing patient data. However, the data from different institutions are usually heterogeneous across institutions, which may reduce the performance of models trained using federated learning. In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning. Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage the federated model training an unbiased estimator of the target data distribution. We compare SplitAVG with seven state-of-the-art federated learning methods, using centrally hosted training data as the baseline on a suite of both synthetic and real-world federated datasets. We find that the performance of models trained using all the comparison federated learning methods degraded significantly with the increasing degrees of data heterogeneity. In contrast, SplitAVG method achieves comparable results to the baseline method under all heterogeneous settings, that it achieves 96.2% of the accuracy and 110.4% of the mean absolute error obtained by the baseline in a diabetic retinopathy binary classification dataset and a bone age prediction dataset, respectively, on highly heterogeneous data partitions. We conclude that SplitAVG method can effectively overcome the performance drops from variability in data distributions across institutions. Experimental results also show that SplitAVG can be adapted to different base networks and generalized to various types of medical imaging tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from the over-smoothing problem, where node representations tend to be indistinguishable as more layers are stacked up. The theoretical research to date on deep GCNs has focused primarily on expressive power rather than trainability, an optimization perspective. Compared to expressivity, trainability attempts to address a more fundamental question: Given a sufficiently expressive space of models, can we successfully find a good solution via gradient descent-based optimizers? This work fills this gap by exploiting the Graph Neural Tangent Kernel (GNTK), which governs the optimization trajectory under gradient descent for wide GCNs. We formulate the asymptotic behaviors of GNTK in the large depth, which enables us to reveal the dropping trainability of wide and deep GCNs at an exponential rate in the optimization process. Additionally, we extend our theoretical framework to analyze residual connection-based techniques, which are found to be merely able to mitigate the exponential decay of trainability mildly. Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally. Experimental evaluation consistently confirms using our proposed method can achieve better results compared to relevant counterparts with both infinite-width and finite-width.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Anomalous interfacial dynamics of single proton charges in binary aqueous solutions

Understanding the dynamics of charge exchange between a solid surface and a liquid is fundamental to various situations, ranging from nanofiltration to catalysis and electrochemistry. Charge transfer is ultimately determined by physicochemical processes (surface group dissociation, ion adsorption, etc...) occurring in the few layers of molecules at the interface between the solid and the liquid. Unfortunately, these processes remain largely uncharted due to the experimental challenges in probing interfacial charge dynamics with sufficiently high spatial and temporal resolution. Here, we resolve at the single-charge scale, the dynamics of proton charges at the interface between an hBN crystal and binary mixtures of water and organic amphiphilic solvents (e.g. alcohol), evidencing a dramatic influence of solvation on interfacial dynamics. Our observations rely on the application of spectral Single Molecule Localization Microscopy (sSMLM) to two types of optically active defects at the hBN surface, which act as intrinsic optical markers for both surface protonation and interaction with apolar alkyl groups of the organic solvent. We use sSMLM to reveal interfacial proton charge transport as a succession of jumps between the titratable surface defects, mediated by the transport of the solvated proton charge along the solid/liquid interface. By changing the relative concentration of water in binary mixtures, we evidence a non-trivial effect on interfacial proton charge dynamics, leading at intermediate water concentration to an increased affinity of the proton charge to the solid surface, accompanied by an increased surface diffusivity. These measurements confirm the strong role of solvation on interfacial proton charge transport and establish the potential of single-molecule localization techniques to probe a wide range of dynamic processes at solid/liquid interfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Exploiting Deep Learning for Secure Transmission in an Underlay Cognitive Radio Network

This paper investigates a machine learning-based power allocation design for secure transmission in a cognitive radio (CR) network. In particular, a neural network (NN)-based approach is proposed to maximize the secrecy rate of the secondary receiver under the constraints of total transmit power of secondary transmitter, and the interference leakage to the primary receiver, within which three different regularization schemes are developed. The key advantage of the proposed algorithm over conventional approaches is the capability to solve the power allocation problem with both perfect and imperfect channel state information. In a conventional setting, two completely different optimization frameworks have to be designed, namely the robust and non-robust designs. Furthermore, conventional algorithms are often based on iterative techniques, and hence, they require a considerable number of iterations, rendering them less suitable in future wireless networks where there are very stringent delay constraints. To meet the unprecedented requirements of future ultra-reliable low-latency networks, we propose an NN-based approach that can determine the power allocation in a CR network with significantly reduced computational time and complexity. As this trained NN only requires a small number of linear operations to yield the required power allocations, the approach can also be extended to different delay sensitive applications and services in future wireless networks. When evaluate the proposed method versus conventional approaches, using a suitable test set, the proposed approach can achieve more than 94% of the secrecy rate performance with less than 1% computation time and more than 93% satisfaction of interference leakage constraints. These results are obtained with significant reduction in computational time, which we believe that it is suitable for future real-time wireless applications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Accurate RGB-D Salient Object Detection via Collaborative Learning

Benefiting from the spatial cues embedded in depth images, recent progress on RGB-D saliency detection shows impressive ability on some challenge scenarios. However, there are still two limitations. One hand is that the pooling and upsampling operations in FCNs might cause blur object boundaries. On the other hand, using an additional depth-network to extract depth features might lead to high computation and storage cost. The reliance on depth inputs during testing also limits the practical applications of current RGB-D models. In this paper, we propose a novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way, which solves those problems tactfully. The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries. Depth and saliency learning is innovatively integrated into the high-level feature learning process in a mutual-benefit manner. This strategy enables the network to be free of using extra depth networks and depth inputs to make inference. To this end, it makes our model more lightweight, faster and more versatile. Experiment results on seven benchmark datasets show its superior performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DUT-LFSaliency: Versatile Dataset and Light Field-to-RGB Saliency Detection

Light field data exhibit favorable characteristics conducive to saliency detection. The success of learning-based light field saliency detection is heavily dependent on how a comprehensive dataset can be constructed for higher generalizability of models, how high dimensional light field data can be effectively exploited, and how a flexible model can be designed to achieve versatility for desktop computers and mobile devices. To answer these questions, first we introduce a large-scale dataset to enable versatile applications for RGB, RGB-D and light field saliency detection, containing 102 classes and 4204 samples. Second, we present an asymmetrical two-stream model consisting of the Focal stream and RGB stream. The Focal stream is designed to achieve higher performance on desktop computers and transfer focusness knowledge to the RGB stream, relying on two tailor-made modules. The RGB stream guarantees the flexibility and memory/computation efficiency on mobile devices through three distillation schemes. Experiments demonstrate that our Focal stream achieves state-of-the-arts performance. The RGB stream achieves Top-2 F-measure on DUTLF-V2, which tremendously minimizes the model size by 83% and boosts FPS by 5 times, compared with the best performing method. Furthermore, our proposed distillation schemes are applicable to RGB saliency models, achieving impressive performance gains while ensuring flexibility.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Feasibility and A Fast Algorithm for Euclidean Distance Matrix Optimization with Ordinal Constraints

Euclidean distance matrix optimization with ordinal constraints (EDMOC) has found important applications in sensor network localization and molecular conformation. It can also be viewed as a matrix formulation of multidimensional scaling, which is to embed n points in a $r$-dimensional space such that the resulting distances follow the ordinal constraints. The ordinal constraints, though proved to be quite useful, may result in only zero solution when too many are added, leaving the feasibility of EDMOC as a question. In this paper, we first study the feasibility of EDMOC systematically. We show that if $r\ge n-2$, EDMOC always admits a nontrivial solution. Otherwise, it may have only zero solution. The latter interprets the numerical observations of 'crowding phenomenon'. Next we overcome two obstacles in designing fast algorithms for EDMOC, i.e., the low-rankness and the potential huge number of ordinal constraints. We apply the technique developed to take the low rank constraint as the conditional positive semidefinite cone with rank cut. This leads to a majorization penalty approach. The ordinal constraints are left to the subproblem, which is exactly the weighted isotonic regression, and can be solved by the enhanced implementation of Pool Adjacent Violators Algorithm (PAVA). Extensive numerical results demonstrate {the} superior performance of the proposed approach over some state-of-the-art solvers.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-Domain Learning and Identity Mining for Vehicle Re-Identification

This paper introduces our solution for the Track2 in AI City Challenge 2020 (AICITY20). The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID. At first, we propose a multi-domain learning method to joint the real-world and synthetic data to train the model. Then, we propose the Identity Mining method to automatically generate pseudo labels for a part of the testing data, which is better than the k-means clustering. The tracklet-level re-ranking strategy with weighted features is also used to post-process the results. Finally, with multiple-model ensemble, our method achieves 0.7322 in the mAP score which yields third place in the competition. The codes are available at https://github.com/heshuting555/AICITY2020_DMT_VehicleReID.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Real-time Earthquake Early Warning with Deep Learning: Application to the 2016 Central Apennines, Italy Earthquake Sequence

Earthquake early warning systems are required to report earthquake locations and magnitudes as quickly as possible before the damaging S wave arrival to mitigate seismic hazards. Deep learning techniques provide potential for extracting earthquake source information from full seismic waveforms instead of seismic phase picks. We developed a novel deep learning earthquake early warning system that utilizes fully convolutional networks to simultaneously detect earthquakes and estimate their source parameters from continuous seismic waveform streams. The system determines earthquake location and magnitude as soon as one station receives earthquake signals and evolutionarily improves the solutions by receiving continuous data. We apply the system to the 2016 Mw 6.0 earthquake in Central Apennines, Italy and its subsequent sequence. Earthquake locations and magnitudes can be reliably determined as early as four seconds after the earliest P phase, with mean error ranges of 6.8-3.7 km and 0.31-0.23, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Resource Allocation Technique for Hybrid TDMA-NOMA System with Opportunistic Time Assignment

In this paper, we develop a resource allocation technique for a hybrid time division multiple access (TDMA) - non-orthogonal multiple access (NOMA) system with opportunistic time assignment. In particular, the available transmission time is divided into several time-slots, through which multiple users are served by exploiting power-domain NOMA. To fully exploit underlying benefits of this hybrid TDMA-NOMA system, we utilize the available resources efficiently by jointly allocating transmit power and time-slots to several groups of users in the system. Furthermore, these resources are allocated to maximize minimum rate of the users in the system. However, this max-min resource allocation problem is non-convex due to coupled design parameters of time and power allocations. Hence, we exploit a novel second-order cone formulation to overcome this non-convexity issue and develop an iterative algorithm to realize a solution to the original max-min problem. Simulation results show that this joint resource allocation technique has a considerable performance enhancement in terms of both minimum achieved rate and overall system throughput compared to that of the conventional resource allocation technique where equal time-slots are assigned to the groups of users.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Super-resolved optical mapping of reactive sulfur-vacancy in 2D transition metal dichalcogenides

Transition metal dichalcogenides (TMDs) represent an entire new class of semiconducting 2D materials with exciting properties. Defects in 2D TMDs can crucially affect their physical and chemical properties. However, characterization of the presence and spatial distribution of defects is limited either in throughput or in resolution. Here, we demonstrate large area mapping of reactive sulfur-deficient defects in 2D-TMDs coupling single-molecule localization microscopy with fluorescence labeling using thiol chemistry. Our method, reminiscent of PAINT strategies, relies on the specific binding by reversible physisorption of fluorescent probes to sulfur-vacancies via a thiol group and their intermittent emission to apply localization of the labeled defects with a precision down to 15 nm. Tuning the distance between the fluorophore and the docking thiol site allows us to control Föster Resonance Energy Transfer (FRET) process and reveal large structural defects such as grain boundaries and line defects, due to the local irregular lattice structure. Our methodology provides a simple and fast alternative for large-scale mapping of non-radiative defects in 2D materials and paves the way for in-situ and spatially resolved monitoring of the interaction between chemical agent and the defects in 2D materials that has general implications for defect engineering in aqueous condition.

0 citations0 reviewsNo code linkedOpen access