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

Hang Zhang

Hang Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine Learningeess.IVComputation and LanguageArtificial Intelligencecond-mat.mtrl-scieess.SPeess.SYSystems and ControlComputational Geometrycond-mat.str-elData Structures and AlgorithmsDatabasesInformation Theorymath.ITmath.OCphysics.app-phphysics.chem-phphysics.flu-dynquant-phRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
27works
0followers
21topics
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

27 published item(s)

preprint2026arXiv

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual reasoning to enhance the robustness and accuracy of driving decisions. However, the reasoning mechanisms employed in most methods are direct adaptations from general domains, lacking in-depth exploration tailored to autonomous driving scenarios, particularly within visual reasoning modules. In this paper, we propose a driving world model that performs parallel prediction of latent semantic features for consecutive future frames in the bird's-eye-view (BEV) space, thereby enabling long-horizon modeling of future world states. We also introduce an efficient and adaptive text reasoning mechanism that utilizes additional social knowledge and reasoning capabilities to further improve driving performance in challenging long-tail scenarios. We present a novel, efficient, and effective approach that achieves state-of-the-art (SOTA) results on the closed-loop Bench2drive benchmark. Codes are available at: https://github.com/hotdogcheesewhite/DeepSight.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Encoder-Only Image Registration

Learning-based techniques have significantly improved the accuracy and speed of deformable image registration. However, challenges such as reducing computational complexity and handling large deformations persist. To address these challenges, we analyze how convolutional neural networks (ConvNets) influence registration performance using the Horn-Schunck optical flow equation. Supported by prior studies and our empirical experiments, we observe that ConvNets play two key roles in registration: linearizing local intensities and harmonizing global contrast variations. Based on these insights, we propose the Encoder-Only Image Registration (EOIR) framework, designed to achieve a better accuracy-efficiency trade-off. EOIR separates feature learning from flow estimation, employing only a 3-layer ConvNet for feature extraction and a set of 3-layer flow estimators to construct a Laplacian feature pyramid, progressively composing diffeomorphic deformations under a large-deformation model. Results on five datasets across different modalities and anatomical regions demonstrate EOIR's effectiveness, achieving superior accuracy-efficiency and accuracy-smoothness trade-offs. With comparable accuracy, EOIR provides better efficiency and smoothness, and vice versa. The source code of EOIR is publicly available on https://github.com/XiangChen1994/EOIR.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges

Medical image registration is critical for clinical applications, and fair benchmarking of different methods is essential for monitoring ongoing progress in the field. To date, the Learn2Reg 2020-2023 challenges have released several complementary datasets and established metrics for evaluations. Building on this foundation, the 2024 edition expands the challenge's scope to cover a wider range of registration scenarios, particularly in terms of modality diversity and task complexity, by introducing three new tasks, including large-scale multi-modal registration and unsupervised inter-subject brain registration, as well as the first microscopy-focused benchmark within Learn2Reg. The new datasets also inspired new method developments, including invertibility constraints, pyramid features, keypoints alignment and instance optimisation. Visit Learn2Reg at https://learn2reg.grand-challenge.org.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation

Biomedical retrieval-augmented generation (RAG) can ground LLM answers in medical literature, yet long-form outputs often contain isolated unsupported or contradictory claims with safety implications. We introduce MedRAGChecker, a claim-level verification and diagnostic framework for biomedical RAG. Given a question, retrieved evidence, and a generated answer, MedRAGChecker decomposes the answer into atomic claims and estimates claim support by combining evidence-grounded natural language inference (NLI) with biomedical knowledge-graph (KG) consistency signals. Aggregating claim decisions yields answer-level diagnostics that help disentangle retrieval and generation failures, including faithfulness, under-evidence, contradiction, and safety-critical error rates. To enable scalable evaluation, we distill the pipeline into compact biomedical models and use an ensemble verifier with class-specific reliability weighting. Experiments on four biomedical QA benchmarks show that MedRAGChecker reliably flags unsupported and contradicted claims and reveals distinct risk profiles across generators, particularly on safety-critical biomedical relations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satellite-to-street data. We introduce Sat3DGen to address these fundamental challenges, which embodies a geometry-first methodology. This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy, explicitly countering the primary sources of geometric error. This geometry-centric strategy yields a dramatic leap in both 3D accuracy and photorealism. For validation, we first constructed a new benchmark by pairing the VIGOR-OOD test set with high-resolution DSM data. On this benchmark, our method improves geometric RMSE from 6.76m to 5.20m. Crucially, this geometric leap also boosts photorealism, reducing the Fréchet Inception Distance (FID) from $\sim$40 to 19 against the leading method, Sat2Density++, despite using no extra tailored image-quality modules. We demonstrate the versatility of our high-quality 3D assets through diverse downstream applications, including semantic-map-to-3D synthesis, multi-camera video generation, large-scale meshing, and unsupervised single-image Digital Surface Model (DSM) estimation. The code has been released on https://github.com/qianmingduowan/Sat3DGen.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A General Compressive Sensing Construct using Density Evolution

This paper proposes a general framework to design a sparse sensing matrix $\ensuremath{\mathbf{A}}\in \mathbb{R}^{m\times n}$, in a linear measurement system $\ensuremath{\mathbf{y}} = \ensuremath{\mathbf{Ax}}^{\natural} + \ensuremath{\mathbf{w}}$, where $\ensuremath{\mathbf{y}} \in \mathbb{R}^m$, $\ensuremath{\mathbf{x}}^{\natural}\in \RR^n$, and $\ensuremath{\mathbf{w}}$ denote the measurements, the signal with certain structures, and the measurement noise, respectively. By viewing the signal reconstruction from the measurements as a message passing algorithm over a graphical model, we leverage tools from coding theory in the design of low density parity check codes, namely the density evolution, and provide a framework for the design of matrix $\ensuremath{\mathbf{A}}$. Particularly, compared to the previous methods, our proposed framework enjoys the following desirable properties: ($i$) Universality: the design supports both regular sensing and preferential sensing, and incorporates them in a single framework; ($ii$) Flexibility: the framework can easily adapt the design of $\bA$ to a signal $\ensuremath{\mathbf{x}}^{\natural}$ with different underlying structures. As an illustration, we consider the $\ell_1$ regularizer, which correspond to Lasso, for both the regular sensing and preferential sensing scheme. Noteworthy, our framework can reproduce the classical result of Lasso, i.e., $m\geq c_0 k\log(n/k)$ (the regular sensing) with regular design after proper distribution approximation, where $c_0 > 0$ is some fixed constant. We also provide numerical experiments to confirm the analytical results and demonstrate the superiority of our framework whenever a preferential treatment of a sub-block of vector $\bx^{\natural}$ is required.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Backward reachability analysis is essential to synthesizing controllers that ensure the correctness of closed-loop systems. This paper is concerned with developing scalable algorithms that under-approximate the backward reachable sets, for discrete-time uncertain linear and nonlinear systems. Our algorithm sequentially linearizes the dynamics, and uses constrained zonotopes for set representation and computation. The main technical ingredient of our algorithm is an efficient way to under-approximate the Minkowski difference between a constrained zonotopic minuend and a zonotopic subtrahend, which consists of all possible values of the uncertainties and the linearization error. This Minkowski difference needs to be represented as a constrained zonotope to enable subsequent computation, but, as we show, it is impossible to find a polynomial-sized representation for it in polynomial time. Our algorithm finds a polynomial-sized under-approximation in polynomial time. We further analyze the conservatism of this under-approximation technique, and show that it is exact under some conditions. Based on the developed Minkowski difference technique, we detail two backward reachable set computation algorithms to control the linearization error and incorporate nonconvex state constraints. Several examples illustrate the effectiveness of our algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems

Deep reinforcement learning (DRL) has recently shown its success in tackling complex combinatorial optimization problems. When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to flexibly and efficiently deal with multiple subproblems determined by weight decomposition of objectives. This paper proposes a concise meta-learning-based DRL approach. It first trains a meta-model by meta-learning. The meta-model is fine-tuned with a few update steps to derive submodels for the corresponding subproblems. The Pareto front is then built accordingly. Compared with other learning-based methods, our method can greatly shorten the training time of multiple submodels. Due to the rapid and excellent adaptability of the meta-model, more submodels can be derived so as to increase the quality and diversity of the found solutions. The computational experiments on multiobjective traveling salesman problems and multiobjective vehicle routing problem with time windows demonstrate the superiority of our method over most of learning-based and iteration-based approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Online Dynamic Parameter Estimation of an Alkaline Electrolysis System Based on Bayesian Inference

When directly coupled with fluctuating energy sources such as wind and photovoltage power, the alkaline electrolysis (AEL) in a power-to-hydrogen (P2H) system is required to operate flexibly by dynamically adjusting its hydrogen production rate. The flex-ibility characteristics, e.g., loading range and ramping rate, of an AEL system are significantly influenced by some parameters re-lated to the dynamic processes of the AEL system. These parame-ters are usually difficult to measure directly and may even change with time. To accurately evaluate the flexibility of an AEL system in online operation, this paper presents a Bayesian Inference-based Markov Chain Monte Carlo (MCMC) method to estimate these parameters. Meanwhile, posterior joint probability distribu-tions of the estimated parameters are obtained as a byproduct, which provides valuable physical insight into the AEL systems. Experiments on a 25 kW electrolyzer validate the proposed pa-rameter estimation method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Photo-Induced Ultrafast Symmetry Switch in SnSe

Layered tin selenide (SnSe) has recently emerged as a high-performance thermoelectric material with the current record for the figure of merit (ZT) observed in the high-temperature Cmcm phase. So far, access of the Cmcm phase has been mainly obtained via thermal equilibrium methods based on sample heating or application of external pressure, thus restricting the current understanding only to ground-state conditions. Here, we investigate the ultrafast carrier and phononic dynamics in SnSe. Our results demonstrate that optical excitations can transiently switch the point-group symmetry of the crystal from Pnma to Cmcm at room temperature in a few hundreds of femtoseconds with an ultralow threshold for the excitation carrier density. This non-equilibrium Cmcm phase is found to be driven by the displacive excitation of coherent Ag phonons and, given the absence of low-energy thermal phonons, exists in SnSe with the status of 'cold lattice with hot carriers'. Our findings provide important insight for understanding non-equilibrium thermoelectric properties of SnSe.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Structure Learning in Graphical Models from Indirect Observations

This paper considers learning of the graphical structure of a $p$-dimensional random vector $X \in R^p$ using both parametric and non-parametric methods. Unlike the previous works which observe $x$ directly, we consider the indirect observation scenario in which samples $y$ are collected via a sensing matrix $A \in R^{d\times p}$, and corrupted with some additive noise $w$, i.e, $Y = AX + W$. For the parametric method, we assume $X$ to be Gaussian, i.e., $x\in R^p\sim N(μ, Σ)$ and $Σ\in R^{p\times p}$. For the first time, we show that the correct graphical structure can be correctly recovered under the indefinite sensing system ($d < p$) using insufficient samples ($n < p$). In particular, we show that for the exact recovery, we require dimension $d = Ω(p^{0.8})$ and sample number $n = Ω(p^{0.8}\log^3 p)$. For the nonparametric method, we assume a nonparanormal distribution for $X$ rather than Gaussian. Under mild conditions, we show that our graph-structure estimator can obtain the correct structure. We derive the minimum sample number $n$ and dimension $d$ as $n\gtrsim (deg)^4 \log^4 n$ and $d \gtrsim p + (deg\cdot\log(d-p))^{β/4}$, respectively, where deg is the maximum Markov blanket in the graphical model and $β> 0$ is some fixed positive constant. Additionally, we obtain a non-asymptotic uniform bound on the estimation error of the CDF of $X$ from indirect observations with inexact knowledge of the noise distribution. To the best of our knowledge, this bound is derived for the first time and may serve as an independent interest. Numerical experiments on both real-world and synthetic data are provided confirm the theoretical results.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Unified smoke and fire detection in an evolutionary framework with self-supervised progressive data augment

Few researches have studied simultaneous detection of smoke and flame accompanying fires due to their different physical natures that lead to uncertain fluid patterns. In this study, we collect a large image data set to re-label them as a multi-label image classification problem so as to identify smoke and flame simultaneously. In order to solve the generalization ability of the detection model on account of the movable fluid objects with uncertain shapes like fire and smoke, and their not compactible natures as well as the complex backgrounds with high variations, we propose a data augment method by random image stitch to deploy resizing, deforming, position variation, and background altering so as to enlarge the view of the learner. Moreover, we propose a self-learning data augment method by using the class activation map to extract the highly trustable region as new data source of positive examples to further enhance the data augment. By the mutual reinforcement between the data augment and the detection model that are performed iteratively, both modules make progress in an evolutionary manner. Experiments show that the proposed method can effectively improve the generalization performance of the model for concurrent smoke and fire detection.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Marangoni Convection-Driven Laser Fountains and Waves on Free Surfaces of Liquids

It is well accepted that an outward Marangoni convection from a low surface tension region will make the surface depressed. Here, we report that this established perception is only valid for thin liquid films. Using surface laser heating, we show that in deep liquids a laser beam actually pulls up the fluid above the free surface generating fountains with different shapes. Whereas with decreasing liquid depth a transition from fountain to indentation with fountain in-indentation is observed. Further, high-speed imaging reveals a transient surface process before steady elevation is formed, and this dynamic deformation is subsequently utilized to resonantly excite giant surface waves by a modulated laser beam. Computational fluid dynamics models reveal the underlying flow patterns and quantify the depth-dependent and time-resolved surface deformations. Our discoveries and techniques have upended the century-old perception and opened up a new regime of interdisciplinary research and applications of Marangoni-induced interface phenomena and optocapillary fluidic surfaces-the control of fluids with light.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

NeRD: Neural Representation of Distribution for Medical Image Segmentation

We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution. Using NeRD, we propose an end-to-end deep learning model for medical image segmentation that can compensate the negative impact of feature distribution shifting issue caused by commonly used network operations such as padding and pooling. An implicit function is used to represent the parameter space of the feature distribution by querying the image coordinate. With NeRD, the impact of issues such as over-segmenting and missing have been reduced, and experimental results on the challenging white matter lesion segmentation and left atrial segmentation verify the effectiveness of the proposed method. The code is available via https://github.com/tinymilky/NeRD.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

An Efficient Index Method for the Optimal Route Query over Multi-Cost Networks

Smart city has been consider the wave of the future and the route recommendation in networks is a fundamental problem in it. Most existing approaches for the shortest route problem consider that there is only one kind of cost in networks. However, there always are several kinds of cost in networks and users prefer to select an optimal route under the global consideration of these kinds of cost. In this paper, we study the problem of finding the optimal route in the multi-cost networks. We prove this problem is NP-hard and the existing index techniques cannot be used to this problem. We propose a novel partition-based index with contour skyline techniques to find the optimal route. We propose a vertex-filtering algorithm to facilitate the query processing. We conduct extensive experiments on six real-life networks and the experimental results show that our method has an improvement in efficiency by an order of magnitude compared to the previous heuristic algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data

We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file. Unlike existing AutoML frameworks that primarily focus on model/hyperparameter selection, AutoGluon-Tabular succeeds by ensembling multiple models and stacking them in multiple layers. Experiments reveal that our multi-layer combination of many models offers better use of allocated training time than seeking out the best. A second contribution is an extensive evaluation of public and commercial AutoML platforms including TPOT, H2O, AutoWEKA, auto-sklearn, AutoGluon, and Google AutoML Tables. Tests on a suite of 50 classification and regression tasks from Kaggle and the OpenML AutoML Benchmark reveal that AutoGluon is faster, more robust, and much more accurate. We find that AutoGluon often even outperforms the best-in-hindsight combination of all of its competitors. In two popular Kaggle competitions, AutoGluon beat 99% of the participating data scientists after merely 4h of training on the raw data.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Bayesian Learning of Probabilistic Dipole Inversion for Quantitative Susceptibility Mapping

A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation. A deep convolutional neural network (CNN) is used to represent the multivariate Gaussian distribution as the approximated posterior distribution of susceptibility given the input measured field. In PDI, such CNN is firstly trained on healthy subjects dataset with labels by maximizing the posterior Gaussian distribution loss function as used in Bayesian deep learning. When tested on new dataset without any label, PDI updates the pre-trained network in an unsupervised fashion by minimizing the KL divergence between the approximated posterior distribution represented by CNN and the true posterior distribution given the likelihood distribution from known physical model and prior distribution. Based on our experiments, PDI provides additional uncertainty estimation compared to the conventional MAP approach, meanwhile addressing the potential discrepancy issue of CNN when test data deviates from training dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Character Matters: Video Story Understanding with Character-Aware Relations

Different from short videos and GIFs, video stories contain clear plots and lists of principal characters. Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots. Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. However, current VSQA methods merely extract generic visual features from a scene. With such an approach, they remain prone to learning just superficial correlations. In order to attain a genuine understanding of who did what to whom, we propose a novel model that continuously refines character-aware relations. This model specifically considers the characters in a video story, as well as the relations connecting different characters and objects. Based on these signals, our framework enables weakly-supervised face naming through multi-instance co-occurrence matching and supports high-level reasoning utilizing Transformer structures. We train and test our model on the six diverse TV shows in the TVQA dataset, which is by far the largest and only publicly available dataset for VSQA. We validate our proposed approach over TVQA dataset through extensive ablation study.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI

The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce the dependency on training data. Experimental results show that when dealing with the in-vivo k-space data, unrolled optimization network with binary under-sampling block and ST estimator had better reconstruction performance compared to the ones with either U-Net reconstruction network or approximate sampling pattern optimization network, and once trained, the learned optimal sampling pattern worked better than the hand-crafted variable density sampling pattern when deployed with other conventional reconstruction methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

FairNN- Conjoint Learning of Fair Representations for Fair Decisions

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by suppressing protected attributes (b) maintains the information content by minimizing a reconstruction loss and (c) allows for solving a classification task in a fair manner by minimizing the classification error and respecting the equalized odds-based fairness regularized. Our experiments on a variety of datasets demonstrate that such a joint approach is superior to separate treatment of unfairness in representation learning or supervised learning. Additionally, our regularizers can be adaptively weighted to balance the different components of the loss function, thus allowing for a very general framework for conjoint fair representation learning and decision making.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Improving Semantic Segmentation via Self-Training

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Let&#39;s be Humorous: Knowledge Enhanced Humor Generation

The generation of humor is an under-explored and challenging problem. Previous works mainly utilize templates or replace phrases to generate humor. However, few works focus on freer forms and the background knowledge of humor. The linguistic theory of humor defines the structure of a humor sentence as set-up and punchline. In this paper, we explore how to generate a punchline given the set-up with the relevant knowledge. We propose a framework that can fuse the knowledge to end-to-end models. To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model. Furthermore, we create the first humor-knowledge dataset. The experimental results demonstrate that our method can make use of knowledge to generate fluent, funny punchlines, which outperforms several baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ResNeSt: Split-Attention Networks

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The Benefits of Diversity: Permutation Recovery in Unlabeled Sensing from Multiple Measurement Vectors

In &#34;Unlabeled Sensing&#34;, one observes a set of linear measurements of an underlying signal with incomplete or missing information about their ordering, which can be modeled in terms of an unknown permutation. Previous work on the case of a single noisy measurement vector has exposed two main challenges: 1) a high requirement concerning the \emph{signal-to-noise ratio} ($\snr$), i.e., approximately of the order of $n^{5}$, and 2) a massive computational burden in light of NP-hardness in general. In this paper, we study the case of \emph{multiple} noisy measurement vectors (MMVs) resulting from a \emph{common} permutation and investigate to what extent the number of MMVs $m$ facilitates permutation recovery by &#34;borrowing strength&#34;. The above two challenges have at least partially been resolved within our work. First, we show that a large stable rank of the signal significantly reduces the required snr which can drop from a polynomial in $n$ for $m = 1$ to a constant for $m = Ω(\log n)$, where $m$ denotes the number of MMVs and $n$ denotes the number of measurements per MV. This bound is shown to be sharp and is associated with a phase transition phenomenon. Second, we propose a computational scheme for recovering the unknown permutation in practice. For the &#34;oracle case&#34; with the known signal, the maximum likelihood (ML) estimator reduces to a linear assignment problem whose global optimum can be obtained efficiently. For the case in which both the signal and permutation are unknown, the problem is reformulated as a bi-convex optimization problem with an auxiliary variable, which can be solved by the Alternating Direction Method of Multipliers (ADMM). Numerical experiments based on the proposed computational scheme confirm the tightness of our theoretical analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Unveiling the Finite Temperature Physics of Hydrogen Chains via Auxiliary Field Quantum Monte Carlo

The ability to accurately predict the finite temperature properties of realistic quantum solids is central to uncovering new phases and engineering materials with novel properties. Nonetheless, there remain comparatively few many-body techniques capable of elucidating the finite temperature physics of solids from first principles. In this work, we take a significant step towards developing such a technique by generalizing our previous, fully ab initio finite temperature Auxiliary Field Quantum Monte Carlo (FT-AFQMC) method to model periodic solids and employing it to uncover the finite temperature physics of periodic hydrogen chains. Based upon our calculations of these chains&#39; many-body thermodynamic quantities and correlation functions, we outline their metal-insulator and magnetic ordering as a function of both H-H bond distance and temperature. At low temperatures approaching the ground state, we observe both metal-insulator and ferromagnetic-antiferromagnetic crossovers at bond lengths between 0.5 and 0.75 Å. We then demonstrate how this low-temperature ordering evolves into a metallic phase with decreasing magnetic order at higher temperatures. By comparing the features we observe to those previously seen in one-dimensional, half-filled Hubbard models at finite temperature and in ground state hydrogen chains, interestingly, we identify signatures of the Pomeranchuk effect in hydrogen chains for the first time and show that spin and charge excitations that typically arise at distinct temperatures in the Hubbard model are indistinguishably coupled in these systems. Beyond qualitatively revealing the many-body phase behavior of hydrogen chains, our efforts shed light on the further theoretical developments that will be required to construct the phase diagrams of the more complex transition metal, lanthanide, and actinide solids of longstanding interest to physicists.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Vertical CVD Growth of Highly Uniform Transition Metal Dichalcogenides

Two-dimensional (2D) transition metal dichalcogenides (TMDCs) have attracted great attention due to their physical and chemical properties that make them promising in electronics and optoelectronics. Because of the difficulties in controlling concentrations of solid precursors and spatially non-uniform growth dynamics, it is challenging to grow wafer-scale 2D TMDCs with good uniformity and reproducibility so far, which significantly hinders their practical use. Here we report a vertical chemical vapor deposition (VCVD) design to grow monolayer TMDCs with a uniform density and high quality over the whole wafer, and with excellent reproducibility. The use of such VCVD design can easily control the three key growth parameters of precursor concentration, gas flow and temperature, which cannot be done in currently widely-used horizontal CVD system. Statistical results show that VCVD-grown monolayer TMDCs including MoS2 and WS2 are of high uniformity and quality on substrates over centimeter size. We also fabricated multiple van der Waals heterostructures by the one-step transfer of VCVD-grown TMDC samples, owning to its good uniformity. This work opens a way to grow 2D materials with high uniformity and reproducibility on the wafer scale, which can be used for the scalable fabrication of 2D materials and their heterostructures.

0 citations0 reviewsNo code linkedOpen access