arXiv subjects

Zhao Zhang

Publications and source records attributed to Zhao Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2020

Unsupervised Vehicle Re-identification with Progressive Adaptation

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''. These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset.

cs.CV↗

arXiv2020

The Limit of the Batch Size

Large-batch training is an efficient approach for current distributed deep learning systems. It has enabled researchers to reduce the ImageNet/ResNet-50 training from 29 hours to around 1 minute. In this paper, we focus on studying the limit of the batch size. We think it may provide a guidance to AI supercomputer and algorithm designers. We provide detailed numerical optimization instructions for step-by-step comparison. Moreover, it is important to understand the generalization and optimization performance of huge batch training. Hoffer et al. introduced "ultra-slow diffusion" theory to large-batch training. However, our experiments show contradictory results with the conclusion of Hoffer et al. We provide comprehensive experimental results and detailed analysis to study the limitations of batch size scaling and "ultra-slow diffusion" theory. For the first time we scale the batch size on ImageNet to at least a magnitude larger than all previous work, and provide detailed studies on the performance of many state-of-the-art optimization schemes under this setting. We propose an optimization recipe that is able to improve the top-1 test accuracy by 18% compared to the baseline.

cs.LG↗

arXiv2020

Dimer rattling mode induced low thermal conductivity in an excellent acoustic conductor

A solid with larger sound speeds exhibits higher lattice thermal conductivity (k_{lat}). Diamond is a prominent instance where its mean sound speed is 14400 m s-1 and k_{lat} is 2300 W m-1 K-1. Here, we report an extreme exception that CuP2 has quite large mean sound speeds of 4155 m s-1, comparable to GaAs, but the single crystals show a very low lattice thermal conductivity of about 4 W m-1 K-1 at room temperature, one order of magnitude smaller than GaAs. To understand such a puzzling thermal transport behavior, we have thoroughly investigated the atomic structure and lattice dynamics by combining neutron scattering techniques with first-principles simulations. Cu atoms form dimers sandwiched in between the layered P atomic networks and the dimers vibrate as a rattling mode with frequency around 11 meV. This mode is manifested to be remarkably anharmonic and strongly scatters acoustic phonons to achieve the low k_{lat}. Such a dimer rattling behavior in layered structures might offer an unprecedented strategy for suppressing thermal conduction without involving atomic disorder.

cond-mat.mtrl-sci↗

arXiv2020

Observation of E8 Particles in an Ising Chain Antiferromagnet

Near the transverse-field induced quantum critical point of the Ising chain, an exotic dynamic spectrum consisting of exactly eight particles was predicted, which is uniquely described by an emergent quantum integrable field theory with the symmetry of the $E_8$ Lie algebra, but rarely explored experimentally. Here we use high-resolution terahertz spectroscopy to resolve quantum spin dynamics of the quasi-one-dimensional Ising antiferromagnet BaCo$_2$V$_2$O$_8$ in an applied transverse field. By comparing to an analytical calculation of the dynamical spin correlations, we identify $E_8$ particles as well as their two-particle excitations.

cond-mat.str-el↗

arXiv2020

Bilateral Attention Network for RGB-D Salient Object Detection

Most existing RGB-D salient object detection (SOD) methods focus on the foreground region when utilizing the depth images. However, the background also provides important information in traditional SOD methods for promising performance. To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task. Specifically, we introduce a Bilateral Attention Module (BAM) with a complementary attention mechanism: foreground-first (FF) attention and background-first (BF) attention. The FF attention focuses on the foreground region with a gradual refinement style, while the BF one recovers potentially useful salient information in the background region. Benefitted from the proposed BAM module, our BiANet can capture more meaningful foreground and background cues, and shift more attention to refining the uncertain details between foreground and background regions. Additionally, we extend our BAM by leveraging the multi-scale techniques for better SOD performance. Extensive experiments on six benchmark datasets demonstrate that our BiANet outperforms other state-of-the-art RGB-D SOD methods in terms of objective metrics and subjective visual comparison. Our BiANet can run up to 80fps on $224\times224$ RGB-D images, with an NVIDIA GeForce RTX 2080Ti GPU. Comprehensive ablation studies also validate our contributions.

cs.CV↗

arXiv2020

Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications

Despite the wide implementation of machine learning (ML) techniques in traffic flow modeling recently, those data-driven approaches often fall short of accuracy in the cases with a small or noisy dataset. To address this issue, this study presents a new modeling framework, named physics regularized machine learning (PRML), to encode classical traffic flow models (referred as physical models) into the ML architecture and to regularize the ML training process. More specifically, a stochastic physics regularized Gaussian process (PRGP) model is developed and a Bayesian inference algorithm is used to estimate the mean and kernel of the PRGP. A physical regularizer based on macroscopic traffic flow models is also developed to augment the estimation via a shadow GP and an enhanced latent force model is used to encode physical knowledge into stochastic processes. Based on the posterior regularization inference framework, an efficient stochastic optimization algorithm is also developed to maximize the evidence lowerbound of the system likelihood. To prove the effectiveness of the proposed model, this paper conducts empirical studies on a real-world dataset which is collected from a stretch of I-15 freeway, Utah. Results show the new PRGP model can outperform the previous compatible methods, such as calibrated pure physical models and pure machine learning methods, in estimation precision and input robustness.

stat.ML↗

arXiv2020

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized. In this work, we address these problems by developing a novel deep network model called Fully-Convolutional Intensive Feature Flow Neural Network (IntensiveNet). Specifically, we design a further dense block called intensive block to extract the feature information, where the original inputs and two dense blocks are connected tightly. To encode data appropriately, we present the concepts of dense fusion block and further dense fusion opera-tions for our new intensive block. By adding short connections to different layers, the feature flow and coupling between layers are enhanced. We also replace the traditional convolution by depthwise separable convolution to make the operation efficient. To prevent important feature information being lost to a certain extent, we use a convolution operation with stride 2 to replace the original pooling operation in the customary transition layers. The recognition results on large-scale Chinese string and MNIST datasets show that our IntensiveNet can deliver enhanced recog-nition results, compared with other related deep models.

cs.CV↗

arXiv2020

Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery

For subspace recovery, most existing low-rank representation (LRR) models performs in the original space in single-layer mode. As such, the deep hierarchical information cannot be learned, which may result in inaccurate recoveries for complex real data. In this paper, we explore the deep multi-subspace recovery problem by designing a multilayer architecture for latent LRR. Technically, we propose a new Multilayer Collabora-tive Low-Rank Representation Network model termed DeepLRR to discover deep features and deep subspaces. In each layer (>2), DeepLRR bilinearly reconstructs the data matrix by the collabo-rative representation with low-rank coefficients and projection matrices in the previous layer. The bilinear low-rank reconstruc-tion of previous layer is directly fed into the next layer as the input and low-rank dictionary for representation learning, and is further decomposed into a deep principal feature part, a deep salient feature part and a deep sparse error. As such, the coher-ence issue can be also resolved due to the low-rank dictionary, and the robustness against noise can also be enhanced in the feature subspace. To recover the sparse errors in layers accurately, a dynamic growing strategy is used, as the noise level will be-come smaller for the increase of layers. Besides, a neighborhood reconstruction error is also included to encode the locality of deep salient features by deep coefficients adaptively in each layer. Extensive results on public databases show that our DeepLRR outperforms other related models for subspace discovery and clustering.

cs.CV↗

arXiv2020

Convolutional Dictionary Pair Learning Network for Image Representation Learning

Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however whether we can seamlessly integrate them to improve the per-formance is noteworthy exploring. To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework. Generally, the architecture of CDPL-Net includes two convolutional/pooling layers and two dictionary pair learn-ing (DPL) layers in the representation learning module. Besides, it uses two fully-connected layers as the multi-layer perception layer in the nonlinear classification module. In particular, the DPL layer can jointly formulate the discriminative synthesis and analysis representations driven by minimizing the batch based reconstruction error over the flatted feature maps from the convolution/pooling layer. Moreover, DPL layer uses l1-norm on the analysis dictionary so that sparse representation can be delivered, and the embedding process will also be robust to noise. To speed up the training process of DPL layer, the efficient stochastic gradient descent is used. Extensive simulations on real databases show that our CDPL-Net can deliver enhanced performance over other state-of-the-art methods.

cs.CV↗

arXiv2020

Ultimate precision of multi-parameter quantum magnetometry under the parallel scheme

The precise measurement of a magnetic field is one of the most fundamental and important tasks in quantum metrology. Although extensive studies on quantum magnetometry have been carried out over past decades, the ultimate precision that can be achieved for the estimation of all three components of a magnetic field with entangled probe states under the parallel scheme remains unknown. Here we present the ultimate lower bound for the sum of arbitrarily weighted variances in the estimation of all three components of a magnetic field under the parallel scheme and show that this lower bound can be achieved for sufficiently large N. The optimal entangled probe state that achieves the ultimate precision is also explicitly constructed. The obtained precision sets the ultimate limit for the multi-parameter quantum magnetometry under the parallel scheme, which is of fundamental interest and importance in quantum metrology. Our approach also provides a way to characterize the tradeoff among the precisions of multiple parameters that arise from the constraints on the probe states.

quant-ph↗

arXiv2020

Mitochondria in higher plants possess H2 evolving activity which is closely related to complex I

Hydrogenase occupy a central place in the energy metabolism of anaerobic bacteria. Although the structure of mitochondrial complex I is similar to that of hydrogenase, whether it has hydrogen metabolic activity remain unclear. Here, we show that a H2 evolving activity exists in higher plants mitochondria and is closely related to complex I, especially around ubiquinone binding site. The H2 production could be inhibited by rotenone and ubiquinone. Hypoxia could simultaneously promote H2 evolution and succinate accumulation. Redox properties of quinone pool, adjusted by NADH or succinate according to oxygen concentration, acts as a valve to control the flow of protons and electrons and the production of H2. The coupling of H2 evolving activity of mitochondrial complex I with metabolic regulation reveals a more effective redox homeostasis regulation mechanism. Considering the ubiquity of mitochondria in eukaryotes, H2 metabolism might be the innate function of higher organisms. This may serve to explain, at least in part, the broad physiological effects of H2.

q-bio.BM↗

arXiv2019

Dynamic 3-D measurement based on fringe-to-fringe transformation using deep learning

Fringe projection profilometry (FPP) has become increasingly important in dynamic 3-D shape measurement. In FPP, it is necessary to retrieve the phase of the measured object before shape profiling. However, traditional phase retrieval techniques often require a large number of fringes, which may generate motion-induced error for dynamic objects. In this paper, a novel phase retrieval technique based on deep learning is proposed, which uses an end-to-end deep convolution neural network to transform a single or two fringes into the phase retrieval required fringes. When the object's surface is located in a restricted depth, the presented network only requires a single fringe as the input, which otherwise requires two fringes in an unrestricted depth. The proposed phase retrieval technique is first theoretically analyzed, and then numerically and experimentally verified on its applicability for dynamic 3-D measurement.

eess.IV↗

arXiv2019

Deep Self-representative Concept Factorization Network for Representation Learning

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discovering hidden deep semantic features, enhancing the robustness proper-ties of the deep factorization to noise and preserving the local man-ifold structures of deep features. Specifically, DSCF-Net seamlessly integrates the robust deep concept factorization, deep self-expressive representation and adaptive locality preserving feature learning into a unified framework. To discover hidden deep repre-sentations, DSCF-Net designs a hierarchical factorization architec-ture using multiple layers of linear transformations, where the hierarchical representation is performed by formulating the prob-lem as optimizing the basis concepts in each layer to improve the representation indirectly. DSCF-Net also improves the robustness by subspace recovery for sparse error correction firstly and then performs the deep factorization in the recovered visual subspace. To obtain locality-preserving representations, we also present an adaptive deep self-representative weighting strategy by using the coefficient matrix as the adaptive reconstruction weights to keep the locality of representations. Extensive comparison results with several other related models show that DSCF-Net delivers state-of-the-art performance on several public databases.

cs.LG↗

arXiv2019

Stationary State Degeneracy of Open Quantum Systems with Non-Abelian Symmetries

We study the null space degeneracy of open quantum systems with multiple non-Abelian, strong symmetries. By decomposing the Hilbert space representation of these symmetries into an irreducible representation involving the direct sum of multiple, commuting, invariant subspaces we derive a tight lower bound for the stationary state degeneracy. We apply these results within the context of open quantum many-body systems, presenting three illustrative examples: a fully-connected quantum network, the XXX Heisenberg model and the Hubbard model. We find that the derived bound, which scales at least cubically in the system size the $SU(2)$ symmetric cases, is often saturated. Moreover, our work provides a theory for the systematic block-decomposition of a Liouvillian with non-Abelian symmetries, reducing the computational difficulty involved in diagonalising these objects and exposing a natural, physical structure to the steady states - which we observe in our examples.

quant-ph↗

arXiv2019

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

In this paper, we investigate the robust dictionary learning (DL) to discover the hybrid salient low-rank and sparse representation in a factorized compressed space. A Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) model is presented. The setting of J-RFDL aims at improving the data representations by enhancing the robustness to outliers and noise in data, encoding the reconstruction error more accurately and obtaining hybrid salient coefficients with accurate reconstruction ability. Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient. To make the encoding process robust to noise in data, J-RFDL clearly uses sparse L2, 1-norm that can potentially minimize the factorization and reconstruction errors jointly by forcing rows of the reconstruction errors to be zeros. To deliver salient coefficients with good structures to reconstruct given data well, J-RFDL imposes the joint low-rank and sparse constraints on the embedded coefficients with a synthesis dictionary. Based on the hybrid salient coefficients, we also extend J-RFDL for the joint classification and propose a discriminative J-RFDL model, which can improve the discriminating abilities of learnt coeffi-cients by minimizing the classification error jointly. Extensive experiments on public datasets demonstrate that our formulations can deliver superior performance over other state-of-the-art methods.

cs.LG↗

arXiv2019

Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition

Deep convolutional neural networks have largely benefited computer vision tasks. However, the high computational complexity limits their real-world applications. To this end, many methods have been proposed for efficient network learning, and applications in portable mobile devices. In this paper, we propose a novel \underline{M}oving-\underline{M}obile-\underline{Net}work, named M$^2$Net, for landmark recognition, equipped each landmark image with located geographic information. We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy. The above intuition is achieved by our proposed reward function with the input of geo-location and landmarks. We also find that the performance of other portable networks can be improved via our architecture. We construct two landmark image datasets, with each landmark associated with geographic information, over which we conduct extensive experiments to demonstrate that M$^2$Net achieves improved recognition accuracy with comparable complexity.

cs.CV↗

arXiv2019

Robust Triple-Matrix-Recovery-Based Auto-Weighted Label Propagation for Classification

The graph-based semi-supervised label propagation algorithm has delivered impressive classification results. However, the estimated soft labels typically contain mixed signs and noise, which cause inaccurate predictions due to the lack of suitable constraints. Moreover, available methods typically calculate the weights and estimate the labels in the original input space, which typically contains noise and corruption. Thus, the en-coded similarities and manifold smoothness may be inaccurate for label estimation. In this paper, we present effective schemes for resolving these issues and propose a novel and robust semi-supervised classification algorithm, namely, the tri-ple-matrix-recovery-based robust auto-weighted label propa-gation framework (ALP-TMR). Our ALP-TMR introduces a triple matrix recovery mechanism to remove noise or mixed signs from the estimated soft labels and improve the robustness to noise and outliers in the steps of assigning weights and pre-dicting the labels simultaneously. Our method can jointly re-cover the underlying clean data, clean labels and clean weighting spaces by decomposing the original data, predicted soft labels or weights into a clean part plus an error part by fitting noise. In addition, ALP-TMR integrates the au-to-weighting process by minimizing reconstruction errors over the recovered clean data and clean soft labels, which can en-code the weights more accurately to improve both data rep-resentation and classification. By classifying samples in the recovered clean label and weight spaces, one can potentially improve the label prediction results. The results of extensive experiments demonstrated the satisfactory performance of our ALP-TMR.

cs.LG↗

arXiv2019

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning. To achieve powerful representation ability of the available samples, the setting of RA-DPL seamlessly integrates the robust projective dictionary pair learning, locality-adaptive sparse representations and discriminative coding coefficients learning into a unified learning framework. Specifically, RA-DPL improves existing projective dictionary pair learning in four perspectives. First, it applies a sparse l2,1-norm based metric to encode the recon-struction error to deliver the robust projective dictionary pairs, and the l2,1-norm has the potential to minimize the error. Sec-ond, it imposes the robust l2,1-norm clearly on the analysis dictionary to ensure the sparse property of the coding coeffi-cients rather than using the costly l0/l1-norm. As such, the robustness of the data representation and the efficiency of the learning process are jointly considered to guarantee the effi-cacy of our RA-DPL. Third, RA-DPL conceives a structured reconstruction weight learning paradigm to preserve the local structures of the coding coefficients within each class clearly in an adaptive manner, which encourages to produce the locality preserving representations. Fourth, it also considers improving the discriminating ability of coding coefficients and dictionary by incorporating a discriminating function, which can ensure high intra-class compactness and inter-class separation in the code space. Extensive experiments show that our RA-DPL can obtain superior performance over other state-of-the-arts.

cs.CV↗