arXiv subjects

Li Zhang

Publications and source records attributed to Li Zhang.

At least 811 records · Page 45Linked to original sources

arXiv2019

CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis

Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating aspect-specific sentence representations. However, the attention may inherently introduce noise and downgrade the performance. In this paper, we propose constrained attention networks (CAN), a simple yet effective solution, to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism. Specifically, we introduce orthogonal regularization on multiple aspects and sparse regularization on each single aspect. Experimental results on two public datasets demonstrate the effectiveness of our approach. We further extend our approach to multi-task settings and outperform the state-of-the-art methods.

cs.CL↗

arXiv2019

Statistical analysis on X-ray flares from the nucleus and HST-1 knot in the M87 jet

The statistical properties of X-ray flares from two separate locations (nucleus and HST-1) in the M87 jet are investigated to reveal the physical origin of the flares. We analyse the archival \textit{Chandra} data for M87, and identify 14 flares in the nucleus and 9 flares in HST-1. The peak intensity ($I_{\rm{P}}$) and the flaring duration time ($T_{\rm{fl}}$) for each flare are obtained. It is found that the distributions of both $I_{\rm{P}}$ and $T_{\rm{fl}}$ for the nucleus obey a power-law form with a similar index. A similar result is also obtained for HST-1, and no significant inconsistency between the nucleus and HST-1 is found for the indices. Similar to solar X-ray flares, the power-law distributions of the flare event parameters can be well explained by a self-organized criticality (SOC) system, which are triggered by magnetic reconnection. Our results suggest that the flares from nucleus and HST-1 are possibly triggered by magnetic reconnection process. The consistent indices for the distributions of $I_{\rm{P}}$ and $T_{\rm{fl}}$ in the CORE and HST-1 indicate that the dimensions of the energy dissipation of the magnetic reconnection is identical in the two regions. A strong correlation between the flares in the two regions also suggests a similar physical origin for the flares.

astro-ph.HE↗

arXiv2019

A Closed-form Solution to Universal Style Transfer

Universal style transfer tries to explicitly minimize the losses in feature space, thus it does not require training on any pre-defined styles. It usually uses different layers of VGG network as the encoders and trains several decoders to invert the features into images. Therefore, the effect of style transfer is achieved by feature transform. Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing. In this paper, we first propose a novel interpretation by treating it as the optimal transport problem. Then, we demonstrate the relations of our formulation with former works like Adaptive Instance Normalization (AdaIN) and Whitening and Coloring Transform (WCT). Finally, we derive a closed-form solution named Optimal Style Transfer (OST) under our formulation by additionally considering the content loss of Gatys. Comparatively, our solution can preserve better structure and achieve visually pleasing results. It is simple yet effective and we demonstrate its advantages both quantitatively and qualitatively. Besides, we hope our theoretical analysis can inspire future works in neural style transfer. Code is available at https://github.com/lu-m13/OptimalStyleTransfer.

cs.CV↗

arXiv2019

Multi-level Domain Adaptive learning for Cross-Domain Detection

In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can seriously affect the performance of detection models. Previous works use adversarial training to align global features across the domain shift and to achieve image information transfer. However, such methods do not effectively match the distribution of local features, resulting in limited improvement in cross-domain object detection. To solve this problem, we propose a multi-level domain adaptive model to simultaneously align the distributions of local-level features and global-level features. We evaluate our method with multiple experiments, including adverse weather adaptation, synthetic data adaptation, and cross camera adaptation. In most object categories, the proposed method achieves superior performance against state-of-the-art techniques, which demonstrates the effectiveness and robustness of our method.

cs.CV↗

arXiv2019

Magnetic phase transitions of insulating spin-orbit coupled Bose atoms in one-dimensional optical lattices

We consider the insulating spin-orbit coupled Bose atoms confined within one-dimensional optical lattices and explore their ground-state magnetic phase transitions. Under strong interactions, the charge degrees of atoms are frozen and the system can be described by an anisotropic XXZ Heisenberg chain with Dzyaloshinskii-Moriya interaction and transverse field. We apply the matrix product state method to obtain low-energy states and analyze the lowest energy gaps and the ground-state magnetization and correlations. We find when the transverse field is absent, the ground state is a gapped ferromagnetic phase with long-range correlation in the z direction if the interspin s-wave interacting strength is stronger than that of the intraspin one, otherwise it is a gapless Luttinger liquid (LL) phase with algebraic decaying correlation. When the transverse field is turned on, the gapless LL phase is broken, there emerges a long-range correlated phase with ferromagnetic, antiferromagnetic or spiral order, which depends on the DM interaction strength. We believe our study provides a complete understanding of the interplay between SOC and quantum magnetism of spinor atoms in optical lattices.

quant-ph↗

arXiv2019

MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks

In this paper, we present a novel dataset named MVB (Multi View Baggage) for baggage ReID task which has some essential differences from person ReID. The features of MVB are three-fold. First, MVB is the first publicly released large-scale dataset that contains 4519 baggage identities and 22660 annotated baggage images as well as its surface material labels. Second, all baggage images are captured by specially-designed multi-view camera system to handle pose variation and occlusion, in order to obtain the 3D information of baggage surface as complete as possible. Third, MVB has remarkable inter-class similarity and intra-class dissimilarity, considering the fact that baggage might have very similar appearance while the data is collected in two real airport environments, where imaging factors varies significantly from each other. Moreover, we proposed a merged Siamese network as baseline model and evaluated its performance. Experiments and case study are conducted on MVB.

cs.CV↗

arXiv2019

Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible. To solve this problem, we propose a knowledge transfer based shape-consistent generative adversarial network (SC-GAN), which is an annotation-free approach that uses the knowledge from publicly available annotated fundus dataset to segment coronary arteries. The proposed network is trained in an end-to-end fashion, generating and segmenting synthetic images that maintain the background of coronary angiography and preserve the vascular structures of retinal vessels and coronary arteries. We train and evaluate the proposed model on a dataset of 1092 digital subtraction angiography images, and experiments demonstrate the supreme accuracy of the proposed method on coronary arteries segmentation.

eess.IV↗

arXiv2019

Learning a Deep Embedding Model for Zero-Shot Learning

Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the success of deep neural networks that learn an end-to-end model between text and images in other vision problems such as image captioning, very few deep ZSL model exists and they show little advantage over ZSL models that utilise deep feature representations but do not learn an end-to-end embedding. In this paper we argue that the key to make deep ZSL models succeed is to choose the right embedding space. Instead of embedding into a semantic space or an intermediate space, we propose to use the visual space as the embedding space. This is because that in this space, the subsequent nearest neighbour search would suffer much less from the hubness problem and thus become more effective. This model design also provides a natural mechanism for multiple semantic modalities (e.g., attributes and sentence descriptions) to be fused and optimised jointly in an end-to-end manner. Extensive experiments on four benchmarks show that our model significantly outperforms the existing models. Code is available at https://github.com/lzrobots/DeepEmbeddingModel_ZSL

cs.CV↗

arXiv2019

First-principles prediction of a new family of layered topological insulators

Dozens of layered V$_2$IV$_2$VI$_6$ (V=P, As, Sb, Bi, IV=Si, Ge, Sn, Pb, VI=S, Se, Te) materials are investigated, several of which have been successfully synthesized in experiment. Among them, we predict nine strong topological insulators (TIs), two strong topological metals (TMs) and nearly twenty trivial insulators at their equilibrium structures. The TIs are in the (1;111) topological class, with energy gaps ranging from 0.04 to 0.2 eV. The strong TMs and the trivial insulators belong to the (1;111) and (0;000) topological classes, respectively. Small compressive strains easily turn some of the trivial insulators into strong TIs. This study enriches not only the family of topological materials but also the family of van der Waals layered materials, providing promising candidates for the future spintronic devices.

cond-mat.mtrl-sci↗

arXiv2019

Transverse photon spin beyond interfaces

Photons possess spin degree of freedom, corresponding to clockwise and counter clockwise rotating direction of the fields. Photon spin plays an important role in various applications such as optical communications, information processing and sensing. In conventional isotropic media, photon spin is aligned with the propagation direction of light, obeying spin momentum locking. Interestingly, at certain interfaces, the surface waves decaying away from the interface possess a photon spin transverse to its propagation, opening exciting opportunities for observation of spin dependent unidirectional excitation in confined systems. Here we propose and realize transverse photon spin (T-spin) in the interior of a bulk medium, without relying on the presence of any interfaces. We show the complete mapping of the T-spin of surface modes to that of the bulk modes by introducing the coupling between electric and magnetic responses along orthogonal directions, i.e., the bianisotropy, into the medium. We further discover that an interface formed by two bianisotropic media of opposite orientations supports edge-dependent propagating modes with tunable cutoff frequencies. Our results provide a new platform for manipulating the spin orbit interaction of electromagnetic waves.

physics.optics↗

arXiv2019

Efficient Semantic Scene Completion Network with Spatial Group Convolution

We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimensions rather than feature channel dimension. It divides input voxels into different groups, then conducts 3D sparse convolution on these separated groups. As only valid voxels are considered when performing convolution, computation can be significantly reduced with a slight loss of accuracy. The proposed operations are validated on semantic scene completion task, which aims to predict a complete 3D volume with semantic labels from a single depth image. With SGC, we further present an efficient 3D sparse convolutional network, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy. Evaluations are conducted on the SUNCG dataset, achieving state-of-the-art performance and fast speed. Code is available at https://github.com/zjhthu/SGC-Release.git

cs.CV↗

arXiv2019

ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning

Extracting multi-scale information is key to semantic segmentation. However, the classic convolutional neural networks (CNNs) encounter difficulties in achieving multi-scale information extraction: expanding convolutional kernel incurs the high computational cost and using maximum pooling sacrifices image information. The recently developed dilated convolution solves these problems, but with the limitation that the dilation rates are fixed and therefore the receptive field cannot fit for all objects with different sizes in the image. We propose an adaptivescale convolutional neural network (ASCNet), which introduces a 3-layer convolution structure in the end-to-end training, to adaptively learn an appropriate dilation rate for each pixel in the image. Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale. We compare the segmentation results using the classic CNN, the dilated CNN and the proposed ASCNet on two types of medical images (The Herlev dataset and SCD RBC dataset). The experimental results show that ASCNet achieves the highest accuracy. Moreover, the automatically generated dilation rates are positively correlated to the sizes of the objects, confirming the effectiveness of the proposed method.

cs.CV↗

arXiv2019

End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching

Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid on the fusion of contextual semantic information and details. To tackle this problem, we propose a network for disparity estimation based on abundant contextual details and semantic information, called Multi-scale Features Network (MSFNet). First, we design a new structure to encode rich semantic information and fine-grained details by fusing multi-scale features. And we combine the advantages of element-wise addition and concatenation, which is conducive to merge semantic information with details. Second, a guidance mechanism is introduced to guide the network to automatically focus more on the unreliable regions. Third, we formulate the consistency check as an error map, obtained by the low stage features with fine-grained details. Finally, we adopt the consistency checking between the left feature and the synthetic left feature to refine the initial disparity. Experiments on Scene Flow and KITTI 2015 benchmark demonstrated that the proposed method can achieve the state-of-the-art performance.

cs.CV↗

arXiv2019

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks

In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion (where a portion of the image is masked) to generate random transformations of images with portions missing to expand existing labelled datasets. In our work, GAN has been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showedbetween DCGAN cascaded with SSD and SSD itself.

cs.CV↗

arXiv2019

Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

In this paper, we propose an analysis mechanism based structured Analysis Discriminative Dictionary Learning (ADDL) framework. ADDL seamlessly integrates the analysis discriminative dictionary learning, analysis representation and analysis classifier training into a unified model. The applied analysis mechanism can make sure that the learnt dictionaries, representations and linear classifiers over different classes are independent and discriminating as much as possible. The dictionary is obtained by minimizing a reconstruction error and an analytical incoherence promoting term that encourages the sub-dictionaries associated with different classes to be independent. To obtain the representation coefficients, ADDL imposes a sparse l2,1-norm constraint on the coding coefficients instead of using l0 or l1-norm, since the l0 or l1-norm constraint applied in most existing DL criteria makes the training phase time consuming. The codes-extraction projection that bridges data with the sparse codes by extracting special features from the given samples is calculated via minimizing a sparse codes approximation term. Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers. Thus, the classification approach of our model is very efficient, because it can avoid the extra time-consuming sparse reconstruction process with trained dictionary for each new test data as most existing DL algorithms. Simulations on real image databases demonstrate that our ADDL model can obtain superior performance over other state-of-the-arts.

cs.CV↗

arXiv2019

Bloch oscillations of multi-magnon excitations in a Heisenberg XXZ chain

The studies of multi-magnon excitations will extend our understandings of quantum magnetism and strongly correlated matters. Here, by using the time-evolving block decimation algorithm, we investigate the Bloch oscillations of two-magnon excitations under a gradient magnetic field. Through analyzing the symmetry of the Hamiltonian, we derive a rigorous and universal relation between ferromagnetic and anti-ferromagnetic systems. Under strong interactions, in addition to free-magnon Bloch oscillations, there appear fractional bounded-magnon Bloch oscillations which can be understood by an effective single-particle model. To extract the frequencies of Bloch oscillations and determine the gradient of magnetic field, we respectively calculate the fidelity in the time domain and the sub-standard deviation in the frequency domain. Our study not only explore the interaction-induced Bloch oscillations of multi-magnon excitations, but also provides an alternative approach to determine the gradient of magnetic field via ultracold atoms in optical lattices.

quant-ph↗

arXiv2019

Deep Learning based Pedestrian Detection at Distance in Smart Cities

Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test. In this paper, we leveraged GANs and proposed a new architecture with a cascaded Single Shot Detector (SSD) for pedestrian detection at distance, which is yet a challenge due to the varied sizes of pedestrians in videos at distance. To overcome the low-resolution issues in pedestrian detection at distance, DCGAN is employed to improve the resolution first to reconstruct more discriminative features for a SSD to detect objects in images or videos. A crucial advantage of our method is that it learns a multi-scale metric to distinguish multiple objects at different distances under one image, while DCGAN serves as an encoder-decoder platform to generate parts of an image that contain better discriminative information. To measure the effectiveness of our proposed method, experiments were carried out on the Canadian Institute for Advanced Research (CIFAR) dataset, and it was demonstrated that the proposed new architecture achieved a much better detection rate, particularly on vehicles and pedestrians at distance, making it highly suitable for smart cities applications that need to discover key objects or pedestrians at distance.

cs.CV↗

arXiv2019

Automated Segmentation of Cervical Nuclei in Pap Smear Images using Deformable Multi-path Ensemble Model

Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image. An accurate nuclei segmentation could thus improve the success rate of cervical cancer screening. In this work, a method of automated cervical nuclei segmentation using Deformable Multipath Ensemble Model (D-MEM) is proposed. The approach adopts a U-shaped convolutional network as a backbone network, in which dense blocks are used to transfer feature information more effectively. To increase the flexibility of the model, we then use deformable convolution to deal with different nuclei irregular shapes and sizes. To reduce the predictive bias, we further construct multiple networks with different settings, which form an ensemble model. The proposed segmentation framework has achieved state-of-the-art accuracy on Herlev dataset with Zijdenbos similarity index (ZSI) of 0.933, and has the potential to be extended for solving other medical image segmentation tasks.

cs.CV↗