arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 379 records · Page 21Linked to original sources

arXiv2020

Improving Uyghur ASR systems with decoders using morpheme-based language models

Uyghur is a minority language, and its resources for Automatic Speech Recognition (ASR) research are always insufficient. THUYG-20 is currently the only open-sourced dataset of Uyghur speeches. State-of-the-art results of its clean and noiseless speech test task haven't been updated since the first release, which shows a big gap in the development of ASR between mainstream languages and Uyghur. In this paper, we try to bridge the gap by ultimately optimizing the ASR systems, and by developing a morpheme-based decoder, MLDG-Decoder (Morpheme Lattice Dynamically Generating Decoder for Uyghur DNN-HMM systems), which has long been missing. We have open-sourced the decoder. The MLDG-Decoder employs an algorithm, named as "on-the-fly composition with FEBABOS", to allow the back-off states and transitions to play the role of a relay station in on-the-fly composition. The algorithm empowers the dynamically generated graph to constrain the morpheme sequences in the lattices as effectively as the static and fully composed graph does when a 4-Gram morpheme-based Language Model (LM) is used. We have trained deeper and wider neural network acoustic models, and experimented with three kinds of decoding schemes. The experimental results show that the decoding based on the static and fully composed graph reduces state-of-the-art Word Error Rate (WER) on the clean and noiseless speech test task in THUYG-20 to 14.24%. The MLDG-Decoder reduces the WER to 14.54% while keeping the memory consumption reasonable. Based on the open-sourced MLDG-Decoder, readers can easily reproduce the experimental results in this paper.

cs.CL↗

arXiv2020

Sharp-interface model for simulating solid-state dewetting in three dimensions

The problem of simulating solid-state dewetting of thin films in three dimensions (3D) by using a sharp-interface approach is considered in this paper. Based on the thermodynamic variation, a speed method is used for calculating the first variation to the total surface energy functional. The speed method shares more advantages than the traditional use of parameterized curves (or surfaces), e.g., it is more intrinsic and its variational structure (related with Cahn-Hoffman $\boldsymbolξ$-vector) is clearer and more direct. By making use of the first variation, necessary conditions for the equilibrium shape of the solid-state dewetting problem is given, and a kinetic sharp-interface model which includes the surface energy anisotropy is also proposed. This sharp-interface model describes the interface evolution in 3D which occurs through surface diffusion and contact line migration. By solving the proposed model, we perform lots of numerical simulations to investigate the evolution of patterned films, e.g., the evolution of a short cuboid and pinch-off of a long cuboid. Numerical simulations in 3D demonstrate the accuracy and efficacy of the sharp-interface approach to capture many of the complexities observed in solid-state dewetting experiments.

cond-mat.soft↗

arXiv2020

Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

Due to its potential wide applications in video surveillance and other computer vision tasks like tracking, person re-identification (ReID) has become popular and been widely investigated. However, conventional person re-identification can only handle RGB color images, which will fail at dark conditions. Thus RGB-infrared ReID (also known as Infrared-Visible ReID or Visible-Thermal ReID) is proposed. Apart from appearance discrepancy in traditional ReID caused by illumination, pose variations and viewpoint changes, modality discrepancy produced by cameras of the different spectrum also exists, which makes RGB-infrared ReID more difficult. To address this problem, we focus on extracting the shared cross-spectrum features of different modalities. In this paper, a novel multi-spectrum image generation method is proposed and the generated samples are utilized to help the network to find discriminative information for re-identifying the same person across modalities. Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem. Combining those two parts together, we also design a one-stream neural network combining the aforementioned methods to extract compact representations of person images, called Cross-spectrum Dual-subspace Pairing (CDP) model. Furthermore, during the training process, we also propose a Dynamic Hard Spectrum Mining method to automatically mine more hard samples from hard spectrum based on the current model state to further boost the performance. Extensive experimental results on two public datasets, SYSU-MM01 with RGB + near-infrared images and RegDB with RGB + far-infrared images, have demonstrated the efficiency and generality of our proposed method.

cs.CV↗

arXiv2020

Power-law scaling for solid-state dewetting of thin films: an Onsager variational approach

We examine the kinetics of surface diffusion-controlled, solid-state dewetting by consideration of the retraction of the contact in a semi-infinite solid thin film on a flat rigid substrate. The analysis is performed within the framework of the Onsager variational principle applied to surface diffusion-controlled morphology evolution. Based on this approach, we derive a simple, reduced-order model to quantitatively analyse the power-law scaling of the dewetting process. Using asymptotic analysis and numerical simulations for the reduced-order model, we find that the retraction distance grows as the $2/5$ power of time and the height of the ridge, adjacent to the contact, grows as the $1/5$ power of time for late time. While the asymptotic analysis focuses on late time and a relatively simple geometric model, the Onsager approach is applicable to all times and descriptions of the morphology of arbitrary complexity.

cond-mat.mtrl-sci↗

arXiv2020

Measurement of the neutron beam profile of the Back-n white neutron facility at CSNS with a Micromegas detector

The Back-n white neutron beam line, which uses back-streaming white neutrons from the spallation target of the China Spallation Neutron Source, is used for nuclear data measurements. A Micromegas-based neutron detector with two variants was specially developed to measure the beam spot distribution for this beam line. In this article, the design, fabrication, and characterization of the detector are described. The results of the detector performance tests are presented, which include the relative electron transparency, the gain and the gain uniformity, and the neutron beam profile reconstruction capability. The result of the first measurement of the Back-n neutron beam spot distribution is also presented.

physics.ins-det↗

arXiv2020

STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Partial person re-identification (ReID) is a challenging task because only partial information of person images is available for matching target persons. Few studies, especially on deep learning, have focused on matching partial person images with holistic person images. This study presents a novel deep partial ReID framework based on pairwise spatial transformer networks (STNReID), which can be trained on existing holistic person datasets. STNReID includes a spatial transformer network (STN) module and a ReID module. The STN module samples an affined image (a semantically corresponding patch) from the holistic image to match the partial image. The ReID module extracts the features of the holistic, partial, and affined images. Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID. Experimental results show that our STNReID obtains 66.7% and 54.6% rank-1 accuracies on partial ReID and partial iLIDS datasets, respectively. These values are at par with those obtained with state-of-the-art methods.

cs.CV↗

arXiv2020

A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification

This study explores a simple but strong baseline for person re-identification (ReID). Person ReID with deep neural networks has progressed and achieved high performance in recent years. However, many state-of-the-art methods design complex network structures and concatenate multi-branch features. In the literature, some effective training tricks briefly appear in several papers or source codes. The present study collects and evaluates these effective training tricks in person ReID. By combining these tricks, the model achieves 94.5% rank-1 and 85.9% mean average precision on Market1501 with only using the global features of ResNet50. The performance surpasses all existing global- and part-based baselines in person ReID. We propose a novel neck structure named as batch normalization neck (BNNeck). BNNeck adds a batch normalization layer after global pooling layer to separate metric and classification losses into two different feature spaces because we observe they are inconsistent in one embedding space. Extended experiments show that BNNeck can boost the baseline, and our baseline can improve the performance of existing state-of-the-art methods. Our codes and models are available at: https://github.com/michuanhaohao/reid-strong-baseline.

cs.CV↗

arXiv2020

Boresight Alignment of DArk Matter Particle Explorer

The DArk Matter Particle Explorer (DAMPE) can measure $γ$-rays in the energy range from a few GeV to about 10 TeV. The direction of each $γ$-ray is reconstructed with respect to the reference system of the DAMPE payload. In this paper, we adopt a maximum likelihood method and use the $γ$-ray data centered around several bright point-like sources to measure and correct the angular deviation from the real celestial coordinate system, the so called ``boresight alignment'' of the DAMPE payload. As a check, we also estimate the boresight alignment for some sets of simulation data with artificial orientation and obtain consistent results. The time-dependent boresight alignment analysis does not show evidence for significant variation of the parameters.

astro-ph.IM↗

arXiv2019

End-to-end Learning of Waveform Generation and Detection for Radar Systems

An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system. Detector and transmitted waveform are trained alternately: For a fixed transmitted waveform, the detector is trained using supervised learning so as to approximate the Neyman-Pearson detector; and for a fixed detector, the transmitted waveform is trained using reinforcement learning based on feedback from the receiver. No prior knowledge is assumed about the target and clutter models. Both transmitter and receiver are implemented as feedforward neural networks. Numerical results show that the proposed end-to-end learning approach is able to obtain a more robust radar performance in clutter and colored noise of arbitrary probability density functions as compared to conventional methods, and to successfully adapt the transmitted waveform to environmental conditions.

eess.SP↗

arXiv2019

Implications on the origin of cosmic rays in light of 10 TV spectral softenings

Precise measurements of the energy spectra of cosmic rays (CRs) show various kinds of features deviating from single power-laws, which give very interesting and important implications on their origin and propagation. Previous measurements from a few balloon and space experiments indicate the existence of spectral softenings around 10 TV for protons (and probably also for Helium nuclei). Very recently, the DArk Matter Particle Explorer (DAMPE) measurement about the proton spectrum clearly reveals such a softening with a high significance. Here we study the implications of these new measurements, as well as the groundbased indirect measurements, on the origin of CRs. We find that a single component of CRs fails to fit the spectral softening and the air shower experiment data simultaneously. In the framework of multiple components, we discuss two possible scenarios, the multiple source population scenario and the background plus nearby source scenario. Both scenarios give reasonable fits to the wide-band data from TeV to 100 PeV energies. Considering the anisotropy observations, the nearby source model is favored.

astro-ph.HE↗

arXiv2019

Adaptive Bayesian SLOPE -- High-dimensional Model Selection with Missing Values

We consider the problem of variable selection in high-dimensional settings with missing observations among the covariates. To address this relatively understudied problem, we propose a new synergistic procedure -- adaptive Bayesian SLOPE -- which effectively combines the SLOPE method (sorted $l_1$ regularization) together with the Spike-and-Slab LASSO method. We position our approach within a Bayesian framework which allows for simultaneous variable selection and parameter estimation, despite the missing values. As with the Spike-and-Slab LASSO, the coefficients are regarded as arising from a hierarchical model consisting of two groups: (1) the spike for the inactive and (2) the slab for the active. However, instead of assigning independent spike priors for each covariate, here we deploy a joint "SLOPE" spike prior which takes into account the ordering of coefficient magnitudes in order to control for false discoveries. Through extensive simulations, we demonstrate satisfactory performance in terms of power, FDR and estimation bias under a wide range of scenarios. Finally, we analyze a real dataset consisting of patients from Paris hospitals who underwent a severe trauma, where we show excellent performance in predicting platelet levels. Our methodology has been implemented in C++ and wrapped into an R package ABSLOPE for public use.

stat.ME↗

arXiv2019

Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification

Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security. However, vehicle Re-ID still suffers a similarity challenge despite the efforts made to solve this problem. This challenge involves distinguishing different instances with nearly identical appearances. In this paper, we propose a novel two-branch stripe-based and attribute-aware deep convolutional neural network (SAN) to learn the efficient feature embedding for vehicle Re-ID task. The two-branch neural network, consisting of stripe-based branch and attribute-aware branches, can adaptively extract the discriminative features from the visual appearance of vehicles. A horizontal average pooling and dimension-reduced convolutional layers are inserted into the stripe-based branch to achieve part-level features. Meanwhile, the attribute-aware branch extracts the global feature under the supervision of vehicle attribute labels to separate the similar vehicle identities with different attribute annotations. Finally, the part-level and global features are concatenated together to form the final descriptor of the input image for vehicle Re-ID. The final descriptor not only can separate vehicles with different attributes but also distinguish vehicle identities with the same attributes. The extensive experiments on both VehicleID and VeRi databases show that the proposed SAN method outperforms other state-of-the-art vehicle Re-ID approaches.

cs.CV↗

arXiv2019

Measurements of differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li reaction in the neutron energy range from 1.0 eV to 2.5 MeV

Differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li, $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 $μ$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid $α$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of $α$-particles were measured from 19.2° to 160.8°. Fitted with the Legendre polynomial series, the ($n, α$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, α$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, α$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations.

nucl-ex↗

arXiv2019

Magnetic Weyl semimetals with diamond structure realized in spinel compounds

Diamond-structure materials have been extensively studied for decades, which form the foundation for most semiconductors and their modern day electronic devices. Here, we discover a e$_g$-orbital ($d_{z^2}$,$d_{x^2-y^2}$ ) model within the diamond lattice (e$_g$-diamond model) that hosts novel topological states. Specifically, the e$_g$-diamond model yields a 3D nodal cage (3D-NC), which is characterized by a $d$-$d$ band inversion protected by two types of degenerate states (i.e., e$_g$-orbital and diamond-sublattice degeneracies). We demonstrate materials realization of this model in the well-known spinel compounds (AB$_2$X$_4$), where the tetrahedron-site cations (A) form the diamond sub-lattice. An ideal half metal with one metallic spin channel formed by well-isolated and half-filled e$_g$-diamond bands, accompanied by a large spin gap (4.36 eV) is discovered in one 4-2 spinel compound (VMg$_2$O$_4$), which becomes a magnetic Weyl semimetal when spin-orbit coupling effect is further considered. Our discovery greatly enriches the physics of diamond structure and spinel compounds, opening a door to their application in spintronics.

cond-mat.mtrl-sci↗

arXiv2019

Linearized Multi-Sampling for Differentiable Image Transformation

We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which performs poorly under severe scale changes, and more importantly, results in poor gradient propagation. This is due to their strict reliance on direct neighbors. Instead, we propose to generate random auxiliary samples in the vicinity of each pixel in the sampled image, and create a linear approximation with their intensity values. We then use this approximation as a differentiable formula for the transformed image. We demonstrate that our approach produces more representative gradients with a wider basin of convergence for image alignment, which leads to considerable performance improvements when training networks for classification tasks. This is not only true under large downsampling, but also when there are no scale changes. We compare our approach with multi-scale sampling and show that we outperform it. We then demonstrate that our improvements to the sampler are compatible with other tangential improvements to Spatial Transformer Networks and that it further improves their performance.

cs.CV↗

arXiv2019

A parametric finite element method for solid-state dewetting problems in three dimensions

We propose a parametric finite element method (PFEM) for efficiently solving the morphological evolution of solid-state dewetting of thin films on a flat rigid substrate in three dimensions (3D). The interface evolution of the dewetting problem in 3D is described by a sharp-interface model, which includes surface diffusion coupled with contact line migration. A variational formulation of the sharp-interface model is presented, and a PFEM is proposed for spatial discretization. For temporal discretization, at each time step, we first update the position of the contact line according to the relaxed contact angle condition; then, by using the position of the new contact line as the boundary condition, we solve a linear algebra system resulted from the discretization of PFEM to obtain the new interface surface for the next step. The well-posedness of the solution of the PFEM is also established. Extensive numerical results are reported to demonstrate the accuracy and efficiency of the proposed PFEM and to show the complexities of the dewetting morphology evolution observed in solid-state dewetting experiments.

physics.comp-ph↗

arXiv2019

Logistic Regression with Missing Covariates -- Parameter Estimation, Model Selection and Prediction within a Joint-Modeling Framework

Logistic regression is a common classification method in supervised learning. Surprisingly, there are very few solutions for performing logistic regression with missing values in the covariates. We suggest a complete approach based on a stochastic approximation version of the EM algorithm to do statistical inference with missing values including the estimation of the parameters and their variance, derivation of confidence intervals and a model selection procedure. We also tackle the problem of prediction for new observations (on a test set) with missing covariate data. The methodology is computationally efficient, and its good coverage and variable selection properties are demonstrated in a simulation study where we contrast its performances to other methods. For instance, the popular approach of multiple imputation by chained equations can lead to estimates that exhibit meaningfully greater biases than the proposed approach. We then illustrate the method on a dataset of severely traumatized patients from Paris hospitals to predict the occurrence of hemorrhagic shock, a leading cause of early preventable death in severe trauma cases. The aim is to consolidate the current red flag procedure, a binary alert identifying patients with a high risk of severe hemorrhage. The methodology is implemented in the R package misaem.

stat.ME↗

arXiv2019

$^{81}$Kr dating at the Guliya ice cap, Tibetan Plateau

We present radiometric $^{81}$Kr dating results for ice samples collected at the outlets of the Guliya ice cap in the western Kunlun Mountains of the Tibetan Plateau. This first application of $^{81}$Kr dating on mid-latitude glacier ice was made possible by recent advances in Atom Trap Trace Analysis, particularly a reduction in the required sample size down to 1 $μ$L STP of krypton. Eight ice blocks were sampled from the bottom of the glacier at three different sites along the southern edges. The $^{81}$Kr data yield upper age limits in the range of 15-74 ka (90% confidence level). This is an order of magnitude lower than the ages exceeding 500 ka which the previous $^{36}$Cl data suggest for the bottom of the Guliya ice core. It is also significantly lower than the widely used chronology up to 110 ka established for the upper part of the core based on $δ^{18}$O in the ice.

physics.geo-ph↗