arXiv subjects

Hui Tang

Publications and source records attributed to Hui Tang.

At least 55 records · Page 3Linked to original sources

arXiv2023

SR-init: An interpretable layer pruning method

Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible solution to the aforementioned challenges. However, the interpretation of existing pruning criteria is always overlooked. To counter this issue, we propose a novel layer pruning method by exploring the Stochastic Re-initialization. Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers. On the basis of this observation, we come up with a layer pruning criterion, i.e., those layers that are not sensitive to stochastic re-initialization (low accuracy drop) produce less contribution to the model and could be pruned with acceptable loss. Afterward, we experimentally verify the interpretability of SR-init via feature visualization. The visual explanation demonstrates that SR-init is theoretically feasible, thus we compare it with state-of-the-art methods to further evaluate its practicability. As for ResNet56 on CIFAR-10 and CIFAR-100, SR-init achieves a great reduction in parameters (63.98% and 37.71%) with an ignorable drop in top-1 accuracy (-0.56% and 0.8%). With ResNet50 on ImageNet, we achieve a 15.59% FLOPs reduction by removing 39.29% of the parameters, with only a drop of 0.6% in top-1 accuracy. Our code is available at https://github.com/huitang-zjut/SR-init.

cs.CV↗

arXiv2023

Machine learning guided discovery of superconducting calcium borocarbides

Pursuit of superconductivity in light-element systems at ambient pressure is of great experimental and theoretical interest. In this work, we combine a machine learning (ML) method with first-principles calculations to efficiently search for the energetically favorable ternary Ca-B-C compounds. Three new layered borocarbides (stable CaBC5 and metastable Ca2BC11 and CaB3C3) are predicted to be phonon-mediated superconductors at ambient pressure. The hexagonal CaB3C3 possesses the highest Tc of 26.05 K among the three compounds. The σ-bonging bands around the Fermi level account for the large electron-phonon coupling (λ = 0.980) of hexagonal CaB3C3. The ML-guided approach opens up a way for greatly accelerating the discovery of new high-Tc superconductors.

cond-mat.mtrl-sci↗

arXiv2023

Unsupervised Domain Adaptation via Distilled Discriminative Clustering

Unsupervised domain adaptation addresses the problem of classifying data in an unlabeled target domain, given labeled source domain data that share a common label space but follow a different distribution. Most of the recent methods take the approach of explicitly aligning feature distributions between the two domains. Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data. Technically, we use clustering objectives based on a robust variant of entropy minimization that adaptively filters target data, a soft Fisher-like criterion, and additionally the cluster ordering via centroid classification. To distill discriminative source information for target clustering, we propose to jointly train the network using parallel, supervised learning objectives over labeled source data. We term our method of distilled discriminative clustering for domain adaptation as DisClusterDA. We also give geometric intuition that illustrates how constituent objectives of DisClusterDA help learn class-wisely pure, compact feature distributions. We conduct careful ablation studies and extensive experiments on five popular benchmark datasets, including a multi-source domain adaptation one. Based on commonly used backbone networks, DisClusterDA outperforms existing methods on these benchmarks. It is also interesting to observe that in our DisClusterDA framework, adding an additional loss term that explicitly learns to align class-level feature distributions across domains does harm to the adaptation performance, though more careful studies in different algorithmic frameworks are to be conducted.

cs.CV↗

arXiv2023

Noise-resistant quantum memory enabled by Hamiltonian engineering

Nuclear spins in quantum dots are promising candidates for fast and scalable quantum memory. By utilizing the hyperfine interaction between the central electron and its surrounding nuclei, quantum information can be transferred to the collective state of the nuclei and be stored for a long time. However, nuclear spin fluctuations in a partially polarized nuclear bath deteriorate the quantum memory fidelity. Here we introduce a noise-resistant protocol to realize fast and high-fidelity quantum memory through Hamiltonian engineering. With analytics and numerics, we show that high-fidelity quantum state transfer between the electron and the nuclear spins is achievable at relatively low nuclear polarizations, due to the strong suppression of nuclear spin noises. For a realistic quantum dot with $10^4$ nuclear spins, a fidelity surpassing 80% is possible at a polarization as low as 30%. Our approach reduces the demand for high nuclear polarization, making experimentally realizing quantum memory in quantum dots more feasible.

cond-mat.mes-hall↗

arXiv2022

Optical-plug-assisted spin vortex in a $^{87}$Rb dipolar spinor Bose-Einstein condensate

Generating a spin vortex in a $^{87}$Rb dipolar spinor Bose-Einstein condensate in a controllable way is still experimentally challenging. We propose an experimentally easy and tunable way to produce spin vortex by varying the potential barrier height and the width of an additionally applied optical plug. A topological phase transition occurs from the trivial single mode approximation phase to the optical-plug-assisted-vortex one, as the barrier height increases and the width lies in an appropriate range. The optical plug causes radial density variation thus the spin vortex is favored by significantly lowering the intrinsic magnetic dipolar energy. A type of coreless spin vortex, different from the conventional polar core vortex, is predicted by our numerical results. Our proposal removes a major obstacle to investigate the topological phase transition in a $^{87}$Rb dipolar spinor BEC.

cond-mat.quant-gas↗

arXiv2022

Transferring Dual Stochastic Graph Convolutional Network for Facial Micro-expression Recognition

Micro-expression recognition has drawn increasing attention due to its wide application in lie detection, criminal detection and psychological consultation. To improve the recognition performance of the small micro-expression data, this paper presents a transferring dual stochastic Graph Convolutional Network (TDSGCN) model. We propose a stochastic graph construction method and dual graph convolutional network to extract more discriminative features from the micro-expression images. We use transfer learning to pre-train SGCNs from macro expression data. Optical flow algorithm is also integrated to extract their temporal features. We fuse both spatial and temporal features to improve the recognition performance. To the best of our knowledge, this is the first attempt to utilize the transferring learning and graph convolutional network in micro-expression recognition task. In addition, to handle the class imbalance problem of dataset, we focus on the design of focal loss function. Through extensive evaluation, our proposed method achieves state-of-the-art performance on SAMM and recently released MMEW benchmarks. Our code will be publicly available accompanying this paper.

cs.CV↗

arXiv2021

Phase transition and enhanced hardness of LaB4 under pressure

The crystalline structures of lanthanum tetraboride, LaB4, under pressure are investigated using a genetic algorithm method coupled with first-principles calculations. We find two low-enthalpy phases for LaB4 as the thermodynamic ground state up to 200 GPa: a phase previously observed in experiments (P4/mbm) and a novel orthorhombic phase (Pnma-I). The P4/mbm phase transforms to the Pnma-I phase at around 106 GPa, accompanied by breakage of the B-octahedron. The P4/mbm phase of LaB4 exhibits a high hardness (30.5 GPa) at ambient conditions, which is comparable to that of the hard material B4C. The hardness of the two low-enthalpy phases increases with pressure. The electronic band structures shows that all of the competitive phases (two stable and two metastable phases) are metallic. Phonon calculations shows the P4/mbm and Pnma-I phases are thermodynamically stable in their respective pressure ranges. This elucidation of the phase transition behavior and hardness of LaB4 provides new knowledge on the interesting high-pressure behaviors of the rare-earth metal borides.

cond-mat.mtrl-sci↗

arXiv2021

MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution

Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence. Inspired by the recent success to consider spatial-temporal information for space-time super-resolution, our main goal in this work is to take full considerations of spatial and temporal correlations within the video sequences of fast dynamic events. To this end, we propose a novel one-stage memory enhanced graph attention network (MEGAN) for space-time video super-resolution. Specifically, we build a novel long-range memory graph aggregation (LMGA) module to dynamically capture correlations along the channel dimensions of the feature maps and adaptively aggregate channel features to enhance the feature representations. We introduce a non-local residual block, which enables each channel-wise feature to attend global spatial hierarchical features. In addition, we adopt a progressive fusion module to further enhance the representation ability by extensively exploiting spatial-temporal correlations from multiple frames. Experiment results demonstrate that our method achieves better results compared with the state-of-the-art methods quantitatively and visually.

cs.CV↗

arXiv2021

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets. To improve discrimination on unseen distribution of point-based geometries in a practical and feasible perspective, this paper proposes a new method of geometry-aware self-training (GAST) for unsupervised domain adaptation of object point cloud classification. Specifically, this paper aims to learn a domain-shared representation of semantic categories, via two novel self-supervised geometric learning tasks as feature regularization. On one hand, the representation learning is empowered by a linear mixup of point cloud samples with their self-generated rotation labels, to capture a global topological configuration of local geometries. On the other hand, a diverse point distribution across datasets can be normalized with a novel curvature-aware distortion localization. Experiments on the PointDA-10 dataset show that our GAST method can significantly outperform the state-of-the-art methods.

cs.CV↗

arXiv2021

Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells react to drug treatment. In this paper, we propose a novel box-based instance segmentation method. Box-based instance segmentation methods capture objects via bounding boxes and then perform individual segmentation within each bounding box region. However, existing methods can hardly differentiate the target from its neighboring objects within the same bounding box region due to their similar textures and low-contrast boundaries. To deal with this problem, in this paper, we propose an object-guided instance segmentation method. Our method first detects the center points of the objects, from which the bounding box parameters are then predicted. To perform segmentation, an object-guided coarse-to-fine segmentation branch is built along with the detection branch. The segmentation branch reuses the object features as guidance to separate target object from the neighboring ones within the same bounding box region. To further improve the segmentation quality, we design an auxiliary feature refinement module that densely samples and refines point-wise features in the boundary regions. Experimental results on three biological image datasets demonstrate the advantages of our method. The code will be available at https://github.com/yijingru/ObjGuided-Instance-Segmentation.

cs.CV↗

arXiv2021

A statistical analysis of pores and micro-cracks in nuclear graphite

Microstructure characterization is of great value to understanding nuclear graphite's properties and irradiation behavior. However, graphite is soft and could be easily damaged during sample preparation. A three-step polishing method involving mechanical polishing, ion milling and rapid oxidation is proposed for graphite. Ion milling is adopted to remove the broken graphite pieces produced by mechanical polishing. Rapid oxidation is then adopted to remove irradiation-induced damage layer during ion milling. The Raman spectra show very low G peak width and ID/IG ratio after rapid oxidation, indicating a surface completely free from artificial defects. The micro-cracks which were conventionally observed via a transmission electron microscope can be observed on rapid-oxidized surface in a scanning electron microscope. By digital image processing, the micro-cracks along with the gas-escape pores in nuclear graphite IG-110 are statistically analyzed. Porosity's distributions on crack (pore) size (spanning from 10 nm to 100 um) are given, which could help to understand and simulate graphite's performances in reactors.

cond-mat.mtrl-sci↗

arXiv2021

On Universal Black-Box Domain Adaptation

In this paper, we study an arguably least restrictive setting of domain adaptation in a sense of practical deployment, where only the interface of source model is available to the target domain, and where the label-space relations between the two domains are allowed to be different and unknown. We term such a setting as Universal Black-Box Domain Adaptation (UB$^2$DA). The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model. To tackle the challenges, we first note that the learning task can be converted as two subtasks of in-class\footnote{In this paper we use in-class (out-class) to describe the classes observed (not observed) in the source black-box model.} discrimination and out-class detection, which can be respectively learned by model distillation and entropy separation. We propose to unify them into a self-training framework, regularized by consistency of predictions in local neighborhoods of target samples. Our framework is simple, robust, and easy to be optimized. Experiments on domain adaptation benchmarks show its efficacy. Notably, by accessing the interface of source model only, our framework outperforms existing methods of universal domain adaptation that make use of source data and/or source models, with a newly proposed (and arguably more reasonable) metric of H-score, and performs on par with them with the metric of averaged class accuracy.

cs.LG↗

arXiv2021

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering

Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA methods strive to learn domain-aligned features such that classifiers trained on the source features can be readily applied to the target ones. Although impressive results have been achieved, these methods have a potential risk of damaging the intrinsic data structures of target discrimination, raising an issue of generalization particularly for UDA tasks in an inductive setting. To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption. Technically, we propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one, and we thus term our method as H-SRDC. Our hybrid model is based on a deep clustering framework that minimizes the Kullback-Leibler divergence between the distribution of network prediction and an auxiliary one, where we impose structural regularization by learning domain-shared classifier and cluster centroids. By enriching the structural similarity assumption, we are able to extend H-SRDC for a pixel-level UDA task of semantic segmentation. We conduct extensive experiments on seven UDA benchmarks of image classification and semantic segmentation. With no explicit feature alignment, our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings. We make our implementation codes publicly available at https://github.com/huitangtang/H-SRDC.

cs.CV↗

arXiv2021

Generation of bottle beam using low-density channel in air

Cylindrical density depressions generated by femtosecond laser pulses filamenting in air for different energy depositions is investigated numerically, by using a set of hydrodynamic equations. The evolution of density profile is calculated for different temperature elevations, the results indicate that the gas density hole is getting shallower and wider with the increasing temperature elevations. A simulation of the propagation inside low-density channel implies a new way to generate a type of bottle beam.

physics.optics↗

arXiv2021

Vicinal and categorical domain adaptation

Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain. Inspiring results have been acquired by learning domain-invariant deep features via domain-adversarial training. However, its parallel design of task and domain classifiers limits the ability to achieve a finer category-level domain alignment. To promote categorical domain adaptation (CatDA), based on a joint category-domain classifier, we propose novel losses of adversarial training at both domain and category levels. Since the joint classifier can be regarded as a concatenation of individual task classifiers respectively for the two domains, our design principle is to enforce consistency of category predictions between the two task classifiers. Moreover, we propose a concept of vicinal domains whose instances are produced by a convex combination of pairs of instances respectively from the two domains. Intuitively, alignment of the possibly infinite number of vicinal domains enhances that of original domains. We propose novel adversarial losses for vicinal domain adaptation (VicDA) based on CatDA, leading to Vicinal and Categorical Domain Adaptation (ViCatDA). We also propose Target Discriminative Structure Recovery (TDSR) to recover the intrinsic target discrimination damaged by adversarial feature alignment. We also analyze the principles underlying the ability of our key designs to align the joint distributions. Extensive experiments on several benchmark datasets demonstrate that we achieve the new state of the art.

cs.CV↗

arXiv2020

Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation

Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we circumvent this problem by proposing an effective method for generating realistic hand poses and show that state-of-the-art algorithms for hand pose estimation can be greatly improved by utilizing the generated hand poses as training data. Specifically, we first adopt an augmented reality (AR) simulator to synthesize hand poses with accurate hand-keypoint labels. Although the synthetic hand poses come with precise joint labels, eliminating the need of manual annotations, they look unnatural and are not the ideal training data. To produce more realistic hand poses, we propose to blend a synthetic hand pose with a real background, such as arms and sleeves. To this end, we develop tonality-alignment generative adversarial networks (TAGANs), which align the tonality and color distributions between synthetic hand poses and real backgrounds, and can generate high quality hand poses. We evaluate TAGAN on three benchmarks, including the RHP, STB, and CMU-PS hand pose datasets. With the aid of the synthesized poses, our method performs favorably against the state-of-the-arts in both 2D and 3D hand pose estimations.

cs.CV↗

arXiv2020

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. In addition, we have made our implementation code publicly available.

cs.LG↗

arXiv2020

Bluff body uses deep-reinforcement-learning trained active flow control to achieve hydrodynamic stealth

We propose a novel active-flow-control (AFC) strategy for bluff bodies to hide their hydrodynamic traces from predators. A group of windward-suction-leeward-blowing (WSLB) actuators are adopted to control the wake of a circular cylinder submerged in a uniform flow. An array of velocity sensors are deployed in the near wake to provide feedback signals. Through the data-driven deep reinforcement learning (DRL), effective control strategies are trained for the WSLB actuation to mitigate the cylinder's hydrodynamic signatures, i.e., strong shears and periodically shed vortices. Only a 0.29% deficit in streamwise velocity is detected, which is a 99.5% reduction from the uncontrolled value. The same control strategy is found to be also effective when the cylinder undergoes transverse vortex-induced vibration (VIV). The findings from this study can shed some lights on the design and operation of underwater structures and robotics to achieve hydrodynamic stealth.

physics.flu-dyn↗