arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 397 records · Page 22Linked to original sources

arXiv2019

Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency

Differentiable render is widely used in optimization-based 3D reconstruction which requires gradients from differentiable operations for gradient-based optimization. The existing differentiable renderers obtain the gradients of rendering via numerical technique which is of low accuracy and efficiency. Motivated by this fact, a differentiable mesh renderer with analytical gradients is proposed. The main obstacle of rasterization based rendering being differentiable is the discrete sampling operation. To make the rasterization differentiable, the pixel intensity is defined as a double integral over the pixel area and the integral is approximated by anti-aliasing with an average filter. Then the analytical gradients with respect to the vertices coordinates can be derived from the continuous definition of pixel intensity. To demonstrate the effectiveness and efficiency of the proposed differentiable renderer, experiments of 3D pose estimation by only multi-viewpoint silhouettes were conducted. The experimental results show that 3D pose estimation without 3D and 2D joints supervision is capable of producing competitive results both qualitatively and quantitatively. The experimental results also show that the proposed differentiable renderer is of higher accuracy and efficiency compared with previous method of differentiable renderer.

cs.CV↗

arXiv2019

A hierarchical Lyapunov-based cascade adaptive control scheme for lower-limb exoskeleton

This paper proposes a hierarchical Lyapunov-based adaptive cascade control scheme for a lower-limb exoskeleton with control saturation. The proposed approach is composed by two control levels with cascade structure. At the higher layer of the structure, a Lyapunov-based back-stepping regulator including adaptive estimation of uncertain parameters and friction force is designed for the leg dynamics, to minimize the deviation of the joint position and its reference value. At the lower layer, a Lyapunov-based neural network adaptive controller is in charge of computing control action for the hydraulic servo system, to follow the force reference computed at the high level, also to compensate for model uncertainty, nonlinearity, and control saturation. The proposed approach shows to be capable in minimizing the interaction torque between machine and human, and suitable for possible imprecise models. The robustness of the closed-loop system is discussed under input constraint. Simulation experiments are reported, which shows that the proposed scheme is effective in imposing smaller interaction torque with respect to PD controller, and in control of models with uncertainty and nonlinearity.

eess.SY↗

arXiv2019

A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout method to inhibit the Overfitting and little efficient in capturing the character information at the more distant site of a long sentence for the word segmentation task. In this work, we propose a sequence-to-sequence transformer model for Chinese word segmentation, which is premised a type of convolutional neural network named temporal convolutional network. The model uses the temporal convolutional network to construct an encoder, and uses one layer of fully-connected neural network to build a decoder, and applies the Dropout method to inhibit the Overfitting, and captures the character information at the distant site of a sentence by adding the layers of the encoder, and binds Conditional Random Fields model to train parameters, and uses the Viterbi algorithm to infer the final result of the Chinese word segmentation. The experiments on traditional Chinese corpora and simplified Chinese corpora show that the performance of Chinese word segmentation of the model is equivalent to the performance of the methods based the Bi-LSTM, and the model has a tremendous growth in parallel computing than the models based the Bi-LSTM.

cs.CL↗

arXiv2019

DmpIRFs and DmpST: DAMPE Instrument Response Functions and Science Tools for Gamma-Ray Data Analysis

GeV gamma ray is an important observation target of DArk Matter Particle Explorer (DAMPE) for indirect dark matter searching and high energy astrophysics. We present in this work a set of accurate instrument response functions of DAMPE (DmpIRFs) including the effective area, point-spread function and energy dispersion that are crucial for the gamma-ray data analysis based on the high statistics simulation data. A dedicated software named DmpST is developed to facilitate the scientific analyses of DAMPE gamma-ray data. Considering the limited number of photons and the angular resolution of DAMPE, the maximum likelihood method is adopted in the DmpST to better disentangle different source components. The basic mathematics and the framework regarding this software are also introduced in this paper.

astro-ph.HE↗

arXiv2019

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

This paper explores a simple and efficient baseline for person re-identification (ReID). Person re-identification (ReID) with deep neural networks has made progress and achieved high performance in recent years. However, many state-of-the-arts methods design complex network structure and concatenate multi-branch features. In the literature, some effective training tricks are briefly appeared in several papers or source codes. This paper will collect and evaluate these effective training tricks in person ReID. By combining these tricks together, the model achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features. Our codes and models are available at https://github.com/michuanhaohao/reid-strong-baseline.

cs.CV↗

arXiv2019

HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing

This paper describes a simple UCCA semantic graph parsing approach. The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery. In this way, we can make use of existing syntactic parsing techniques. Based on the data statistics, we recover discontinuous nodes directly according to the output labels of the constituent parser and use a biaffine classification model to recover the more complex remote edges. The classification model and the constituent parser are simultaneously trained under the multi-task learning framework. We use the multilingual BERT as extra features in the open tracks. Our system ranks the first place in the six English/German closed/open tracks among seven participating systems. For the seventh cross-lingual track, where there is little training data for French, we propose a language embedding approach to utilize English and German training data, and our result ranks the second place.

cs.CL↗

arXiv2019

ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views

In this paper, we introduce the ShopSign dataset, which is a newly developed natural scene text dataset of Chinese shop signs in street views. Although a few scene text datasets are already publicly available (e.g. ICDAR2015, COCO-Text), there are few images in these datasets that contain Chinese texts/characters. Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition. The new dataset has three distinctive characteristics: (1) large-scale: it contains 25,362 Chinese shop sign images, with a total number of 196,010 text-lines. (2) diversity: the images in ShopSign were captured in different scenes, from downtown to developing regions, using more than 50 different mobile phones. (3) difficulty: the dataset is very sparse and imbalanced. It also includes five categories of hard images (mirror, wooden, deformed, exposed and obscure). To illustrate the challenges in ShopSign, we run baseline experiments using state-of-the-art scene text detection methods (including CTPN, TextBoxes++ and EAST), and cross-dataset validation to compare their corresponding performance on the related datasets such as CTW, RCTW and ICPR 2018 MTWI challenge dataset. The sample images and detailed descriptions of our ShopSign dataset are publicly available at: https://github.com/chongshengzhang/shopsign.

cs.CV↗

arXiv2019

An End-to-End Network for Panoptic Segmentation

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing features, which makes the pipeline inefficient to implement. In addition, a heuristic method is usually employed to merge the results. However, the overlapping relationship between object instances is difficult to determine without sufficient context information during the merging process. To address the problems, we propose a novel end-to-end network for panoptic segmentation, which can efficiently and effectively predict both the instance and stuff segmentation in a single network. Moreover, we introduce a novel spatial ranking module to deal with the occlusion problem between the predicted instances. Extensive experiments have been done to validate the performance of our proposed method and promising results have been achieved on the COCO Panoptic benchmark.

cs.CV↗

arXiv2019

Improve Object Detection by Data Enhancement based on Generative Adversarial Nets

The accuracy of the object detection model depends on whether the anchor boxes effectively trained. Because of the small number of GT boxes or object target is invariant in the training phase, cannot effectively train anchor boxes. Improving detection accuracy by extending the dataset is an effective way. We propose a data enhancement method based on the foreground-background separation model. While this model uses a binary image of object target random perturb original dataset image. Perturbation methods include changing the color channel of the object, adding salt noise to the object, and enhancing contrast. The main contribution of this paper is to propose a data enhancement method based on GAN and improve detection accuracy of DSSD. Results are shown on both PASCAL VOC2007 and PASCAL VOC2012 dataset. Our model with 321x321 input achieves 78.7% mAP on the VOC2007 test, 76.6% mAP on the VOC2012 test.

cs.CV↗

arXiv2019

Hiding in the Clouds and Building a Stealth Communication Network

Social networks, instant messages and file sharing systems are common communication means among friends, families, coworkers, etc. Due to concerns of personal privacy, identify thefts, data misuse, freedom of speech and government surveillance, online social or communication networks have provided various options for a user to guard or control his or her personal data. However, for most these services, user data are still accessible by the service providers, which can lead to both liability issues if data breach occurs at the server side and data misuse by the network administrators. To prevent service providers from accessing user data, secure end-to-end user communication is a must, like the one provided by WhatsApp. On the other hand, the services provided by such communication network can still be interfered by an authority. For a communication network to be stealthy, the following features are essential: (1) oblivious service, (2) complete user control and flexibility, and (3) lightweight. In this paper, we first discuss the features and benefits of a stealth communication network (SNET), and then we propose a theoretical framework that can be adopted to implement an SNET. By utilizing the framework and the existing publicly available cloud storage, we present the implementation details of an instance of SNET, named Secret-Share. Last but not least, we discuss the current limitations of Secret-Share and its potential extensions.

cs.CR↗

arXiv2019

A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation

Statistical body shape models are widely used in 3D pose estimation due to their low-dimensional parameters representation. However, it is difficult to avoid self-intersection between body parts accurately. Motivated by this fact, we proposed a novel self-intersection penalty term for statistical body shape models applied in 3D pose estimation. To avoid the trouble of computing self-intersection for complex surfaces like the body meshes, the gradient of our proposed self-intersection penalty term is manually derived from the perspective of geometry. First, the self-intersection penalty term is defined as the volume of the self-intersection region. To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection. Second, the partial derivatives could be easily derived by the normal vectors of neighboring triangles of the vertices. Finally, this penalty term could be applied in gradient-based optimization algorithms to remove the self-intersection of triangular meshes without using any approximation. Qualitative and quantitative evaluations were conducted to demonstrate the effectiveness and generality of our proposed method compared with previous approaches. The experimental results show that our proposed penalty term can avoid self-intersection to exclude unreasonable predictions and improves the accuracy of 3D pose estimation indirectly. Further more, the proposed method could be employed universally in triangular mesh based 3D reconstruction.

cs.CV↗

arXiv2018

Implicit temporal discretization and exact energy conservation for particle methods applied to the Poisson-Boltzmann equation

Wereportonanewmultiscalemethodapproachforthestudyofsystemswith wide separation of short-range forces acting on short time scales and long-range forces acting on much slower scales. We consider the case of the Poisson-Boltzmann equation that describes the long-range forces using the Boltzmann formula (i.e. we assume the medium to be in quasi local thermal equilibrium). We developed a new approach where fields and particle information (mediated by the equations for their moments) are solved self-consistently. The new approach is implicit and numerically stable, providing exact energy conservation. We tested different implementations all leading to exact energy conservation. The new method requires the solution of a large set of non-linear equations. We considered three solution strategies: Jacobian Free Newton Krylov, an alternative, called field hiding, based on hiding part of the residual calculation and replacing them with direct solutions and a Direct Newton Schwarz solver that considers simplified single particle-based Jacobian. The field hiding strategy proves to be the most efficient approach.

physics.comp-ph↗

arXiv2018

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress. However, persons are often occluded by obstacles or other persons in practical scenarios, which makes partial person re-identification non-trivial. In this paper, we propose a spatial-channel parallelism network (SCPNet) in which each channel in the ReID feature pays attention to a given spatial part of the body. The spatial-channel corresponding relationship supervises the network to learn discriminative feature for both holistic and partial person re-identification. The single model trained on four holistic ReID datasets achieves competitive accuracy on these four datasets, as well as outperforms the state-of-the-art methods on two partial ReID datasets without training.

cs.CV↗

arXiv2018

Solid-state dewetting on curved substrates

Based on the thermodynamic variation to the free energy functional, we propose a sharp-interface model for simulating solid-state dewetting of thin films on rigid curved substrates in two dimensions. This model describes the interface evolution which occurs through surface diffusion-controlled mass transport and contact point migration along the curved substrate. Furthermore, the surface energy anisotropy is easily included into the model, and the contact point migration is explicitly described by the relaxed contact angle boundary condition. We implement the mathematical model by a semi-implicit parametric finite element method to study several interesting phenomena, such as "small" particle migration on curved substrates and templated solid-state dewetting on a pre-patterned substrate. Based on ample numerical simulations, we demonstrate that, the migration velocity of a "small" solid particle is proportional to the substrate curvature gradient $\hatκ'$ and inversely proportional to the square root of the area of the particle $\sqrt{A}$, and it decreases when the isotropic Young angle $θ_i$ increases. In addition, we also observe four periodic categories of dewetting on a pre-patterned sinusoidal substrate. Our approach can provide a convenient and powerful tool to exploring how to produce well-organized nanoparticles by making use of template-assisted solid-state dewetting.

cond-mat.mtrl-sci↗

arXiv2018

Application of Onsager's variational principle to the dynamics of a solid toroidal island on a substrate

In this paper, we consider the capillarity-driven evolution of a solid toroidal island on a flat rigid substrate, where mass transport is controlled by surface diffusion. This problem is representative of the geometrical complexity associated with the solid-state dewetting of thin films on substrates. We apply Onsager's variational principle to develop a general approach for describing surface diffusion-controlled problems. Based on this approach, we derive a simple, reduced-order model and obtain an analytical expression for the rate of island shrinking and validate this prediction by numerical simulations based on a full, sharp-interface model. We find that the rate of island shrinking is proportional to the material constants $B$ and the surface energy density $γ_0$, and is inversely proportional to the island volume $V_0$. This approach represents a general tool for modeling interface diffusion-controlled morphology evolution.

cond-mat.soft↗

arXiv2018

Distributing and Obfuscating Firewalls via Oblivious Bloom Filter Evaluation

Firewalls have long been in use to protect local networks from threats of the larger Internet. Although firewalls are effective in preventing attacks initiated from outside, they are vulnerable to insider threats, e.g., malicious insiders may access and alter firewall configurations, and disable firewall services. In this paper, we develop an innovative distributed architecture to obliviously manage and evaluate firewalls to prevent both insider and external attacks oriented to the firewalls. Our proposed structure alleviates these issues by obfuscating the firewall rules or policies themselves, then distributing the function of evaluating these rules across multiple servers. Thus, both accessing and altering the rules are considerably more difficult thereby providing better protection to the local network as well as greater security for the firewall itself. We achieve this by integrating multiple areas of research such as secret sharing schemes and multi-party computation, as well as Bloom filters and Byzantine agreement protocols. Our resulting solution is an efficient and secure means by which a firewall may be distributed, and obfuscated while maintaining the ability for multiple servers to obliviously evaluate its functionality.

cs.CR↗

arXiv2018

First Integrated Implosion Experiment of Three-Axis Cylindrical Hohlraum at the SGIII Laser Facility

The first integrated implosion experiment of three-axis cylindrical hohlraum (TACH) was accomplished at the SGIII laser facility. 24 laser beams of the SGIII laser facility were carefully chosen and quasi-symmetrically injected into the TACH, in which a highly symmetric radiation filed was generated with a peak radiation temperature of ~190eV. Driven by the radiation field, the neutron yield of a deuterium gas filled capsule reached ~1e9, and the corresponding yield over clean (YOC) was ~40% for a convergence ratio (Cr) of ~17. The X-ray self-emission image of imploded capsule cores was nearly round, and the backscatter fraction of laser beams was less than 1.25%. This experiment preliminarily demonstrated the major performance of TACH, such as the robustness of symmetry, and a laser plasma instability (LPI) behavior similar to that of the outer ring of traditional cylindrical hohlraum.

physics.plasm-ph↗

arXiv2018

SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

Many current successful Person Re-Identification(ReID) methods train a model with the softmax loss function to classify images of different persons and obtain the feature vectors at the same time. However, the underlying feature embedding space is ignored. In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously. A balanced sampling strategy is also introduced. Finally, we propose a convolutional neural network called SphereReID adopting Sphere Softmax and training a single model end-to-end with a new warming-up learning rate schedule on four challenging datasets including Market-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results demonstrate that this single model outperforms the state-of-the-art methods on all four datasets without fine-tuning or re-ranking. For example, it achieves 94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on DukeMTMC-reID. The code and trained weights of our model will be released.

cs.CV↗