arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 451 records · Page 25Linked to original sources

arXiv2018

Testing Untestable Neural Machine Translation: An Industrial Case

Neural Machine Translation (NMT) has been widely adopted recently due to its advantages compared with the traditional Statistical Machine Translation (SMT). However, an NMT system still often produces translation failures due to the complexity of natural language and sophistication in designing neural networks. While in-house black-box system testing based on reference translations (i.e., examples of valid translations) has been a common practice for NMT quality assurance, an increasingly critical industrial practice, named in-vivo testing, exposes unseen types or instances of translation failures when real users are using a deployed industrial NMT system. To fill the gap of lacking test oracle for in-vivo testing of an NMT system, in this paper, we propose a new approach for automatically identifying translation failures, without requiring reference translations for a translation task; our approach can directly serve as a test oracle for in-vivo testing. Our approach focuses on properties of natural language translation that can be checked systematically and uses information from both the test inputs (i.e., the texts to be translated) and the test outputs (i.e., the translations under inspection) of the NMT system. Our evaluation conducted on real-world datasets shows that our approach can effectively detect targeted property violations as translation failures. Our experiences on deploying our approach in both production and development environments of WeChat (a messenger app with over one billion monthly active users) demonstrate high effectiveness of our approach along with high industry impact.

cs.CL↗

arXiv2018

Common-Message Broadcast Channels with Feedback in the Nonasymptotic Regime: Stop Feedback

We investigate the maximum coding rate for a given average blocklength and error probability over a K-user discrete memoryless broadcast channel for the scenario where a common message is transmitted using variable-length stop-feedback codes. For the point-to-point case, Polyanskiy et al. (2011) demonstrated that variable-length coding combined with stop-feedback significantly increases the speed of convergence of the maximum coding rate to capacity. This speed-up manifests itself in the absence of a square-root penalty in the asymptotic expansion of the maximum coding rate for large blocklengths, i.e., zero dispersion. In this paper, we present nonasymptotic achievability and converse bounds on the maximum coding rate of the common-message K-user discrete memoryless broadcast channel, which strengthen and generalize the ones reported in Trillingsgaard et al. (2015) for the two-user case. An asymptotic analysis of these bounds reveals that zero dispersion cannot be achieved for certain common-message broadcast channels (e.g., the binary symmetric broadcast channel). Furthermore, we identify conditions under which our converse and achievability bounds are tight up to the second order. Through numerical evaluations, we illustrate that our second-order expansions approximate accurately the maximum coding rate and that the speed of convergence to capacity is indeed slower than for the point-to-point case.

cs.IT↗

arXiv2018

Common-Message Broadcast Channels with Feedback in the Nonasymptotic Regime: Full Feedback

We investigate the maximum coding rate achievable on a two-user broadcast channel for the case where a common message is transmitted with feedback using either fixed-blocklength codes or variable-length codes. For the fixed-blocklength-code setup, we establish nonasymptotic converse and achievability bounds. An asymptotic analysis of these bounds reveals that feedback improves the second-order term compared to the no-feedback case. In particular, for a certain class of antisymmetric broadcast channels, we show that the dispersion is halved. For the variable-length-code setup, we demonstrate that the channel dispersion is zero.

cs.IT↗

arXiv2018

Benchmarking and validation of global model code for negative hydrogen ion sources

Benchmarking and validation are prerequisite for using simulation codes as predictive tools. In this work, we have developed a Global Model for Negative Hydrogen Ion Source (GMNHIS) and performed benchmarking of GMNHIS against another independently developed code, Global Enhanced Vibrational Kinetic Model (GEVKM). This is the first study to present quite comprehensive benchmarking test of this kind for models of negative hydrogen ion sources (NHIS), and very good agreement has been achieved for electron temperature, vibrational distribution function (VDF) of hydrogen molecules, and n_H^-/n_e ratio. The small discrepancies in number densities of negative hydrogen ions, positive ions, as well as hydrogen atoms can be attributed to the differences in the predicted electron number density for given discharge power. Higher electron number density obtained with GMNHIS is possibly due to fewer dissociation channels accounted for in GMNHIS, leading to smaller energy loss. In addition, we validated GMNHIS against experimental data obtained in an electron cyclotron resonance (ECR) discharge used for H^- production. The model qualitatively (and even quantitatively for certain conditions) reproduces the experimental H^- number density. The H^- number density as a function of pressure first increases at pressures below 12 mTorr, and then saturates for higher pressures. This dependence was analyzed by evaluating contributions from different reaction pathways to the creation and loss of the H^- ions. The developed codes can be used for predicting the H^- production, improving the performance of NHIS, and ultimately optimizing the parameters of negative ion beams for ITER.

physics.plasm-ph↗

arXiv2018

Beta-Beta Bounds: Finite-Blocklength Analog of the Golden Formula

It is well known that the mutual information between two random variables can be expressed as the difference of two relative entropies that depend on an auxiliary distribution, a relation sometimes referred to as the golden formula. This paper is concerned with a finite-blocklength extension of this relation. This extension consists of two elements: 1) a finite-blocklength channel-coding converse bound by Polyanskiy and Verdú (2014), which involves the ratio of two Neyman-Pearson $β$ functions (beta-beta converse bound); and 2) a novel beta-beta channel-coding achievability bound, expressed again as the ratio of two Neyman-Pearson $β$ functions. To demonstrate the usefulness of this finite-blocklength extension of the golden formula, the beta-beta achievability and converse bounds are used to obtain a finite-blocklength extension of Verdú's (2002) wideband-slope approximation. The proof parallels the derivation of the latter, with the beta-beta bounds used in place of the golden formula. The beta-beta (achievability) bound is also shown to be useful in cases where the capacity-achieving output distribution is not a product distribution due to, e.g., a cost constraint or structural constraints on the codebook, such as orthogonality or constant composition. As an example, the bound is used to characterize the channel dispersion of the additive exponential-noise channel and to obtain a finite-blocklength achievability bound (the tightest to date) for multiple-input multiple-output Rayleigh-fading channels with perfect channel state information at the receiver.

cs.IT↗

arXiv2018

Recovery based finite element method for biharmonic equation in two dimensional

We design and numerically validate a recovery based linear finite element method for solving the biharmonic equation. The main idea is to replace the gradient operator $\nabla$ on linear finite element space by $G(\nabla)$ in the weak formulation of the biharmonic equation, where $G$ is the recovery operator which recovers the piecewise constant function into the linear finite element space. By operator $G$, Laplace operator $Δ$ is replaced by $\nabla\cdot G(\nabla)$. Furthermore the boundary condition on normal derivative $\nabla u\cdot \pmb{n}$ is treated by the boundary penalty method. The explicit matrix expression of the proposed method is also introduced. Numerical examples on uniform and adaptive meshes are presented to illustrate the correctness and effectiveness of the proposed method.

math.NA↗

arXiv2018

Evaluating Non-Motorized Transport Popularity of Urban Roads by Sports GPS Tracks

Non-motorized transport is becoming increasingly important in urban development of cities in China. How to evaluate the non-motorized transport popularity of urban roads is an interesting question to study. The great amount of tracking data generated by smart mobile devices give us opportunities to solve this problem. This study aims to provide a data driven method for evaluating the popularity (walkability and bikeability) of urban non-motorized transport system. This paper defines a p-index to evaluate the popular degree of road segments which is based on the cycling, running, and walking GPS track data from outdoor activities logging applications. According to the p-index definition, this paper evaluates the non-motorized transport popularity of urban area in Wuhan city within different temporal periods.

cs.CY↗

arXiv2018

3D Human Pose Estimation in the Wild by Adversarial Learning

Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations. Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild. We also observe that a carefully designed information source for the discriminator is essential to boost the performance. Thus, we design a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator. The efficacy of our adversarial learning framework with the new geometric descriptor has been demonstrated through extensive experiments on widely used public benchmarks. Our approach significantly improves the performance compared with previous state-of-the-art approaches.

cs.CV↗

arXiv2018

Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc. Direct estimation of 3D pose, body shape or motion on these low-quality data has been traditionally challenging.In this paper, we present a graph-based non-rigid shape registration framework that can simultaneously recover 3D human body geometry and estimate pose/motion at high fidelity.Our approach first generates a global full-body template by registering all poses in the acquired motion sequence.We then construct a deformable graph by utilizing the rigid components in the global template. We directly warp the global template graph back to each motion frame in order to fill in missing geometry. Specifically, we combine local rigidity and temporal coherence constraints to maintain geometry and motion consistencies. Comprehensive experiments on various scenes show that our method is accurate and robust even in the presence of drastic motions.

cs.CV↗

arXiv2017

Identity-Aware Textual-Visual Matching with Latent Co-attention

Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware two-stage framework for the textual-visual matching problem. Our stage-1 CNN-LSTM network learns to embed cross-modal features with a novel Cross-Modal Cross-Entropy (CMCE) loss. The stage-1 network is able to efficiently screen easy incorrect matchings and also provide initial training point for the stage-2 training. The stage-2 CNN-LSTM network refines the matching results with a latent co-attention mechanism. The spatial attention relates each word with corresponding image regions while the latent semantic attention aligns different sentence structures to make the matching results more robust to sentence structure variations. Extensive experiments on three datasets with identity-level annotations show that our framework outperforms state-of-the-art approaches by large margins.

cs.CV↗

arXiv2017

Learning Feature Pyramids for Human Pose Estimation

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens. Although pyramid methods are widely used to handle scale changes at inference time, learning feature pyramids in deep convolutional neural networks (DCNNs) is still not well explored. In this work, we design a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs. Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multi-branch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently. Therefore, we provide theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. We investigate our method on two standard benchmarks for human pose estimation. Our approach obtains state-of-the-art results on both benchmarks. Code is available at https://github.com/bearpaw/PyraNet.

cs.CV↗

arXiv2017

Designing high-performance composite joints close to parent materials of aluminum matrix composites

Composite joints with high-performance close to the parent materials of aluminum matrix composites were fabricated by a new joining technology assisted by ultrasonic vibration. We found both the microstructure and the mechanical performance were systematically dependent on the volume fraction and the distribution of reinforcement particles in the bond region. This study can be generalized to the bonding of other ceramic-reinforced metal matrix composites.

cond-mat.mtrl-sci↗

arXiv2017

Wiretap Channels: Nonasymptotic Fundamental Limits

This paper investigates the maximal secret communication rate over a wiretap channel subject to reliability and secrecy constraints at a given blocklength. New achievability and converse bounds are derived, which are uniformly tighter than existing bounds, and lead to the tightest bounds on the second-order coding rate for discrete memoryless and Gaussian wiretap channels. The exact second-order coding rate is established for semi-deterministic wiretap channels, which characterizes the optimal tradeoff between reliability and secrecy in the finite-blocklength regime. Underlying our achievability bounds are two new privacy amplification results, which not only refine the existing results, but also achieve stronger notions of secrecy.

cs.IT↗

arXiv2017

State-Dependent Gaussian Multiple Access Channels: New Outer Bounds and Capacity Results

This paper studies a two-user state-dependent Gaussian multiple-access channel (MAC) with state noncausally known at one encoder. Two scenarios are considered: i) each user wishes to communicate an independent message to the common receiver, and ii) the two encoders send a common message to the receiver and the non-cognitive encoder (i.e., the encoder that does not know the state) sends an independent individual message (this model is also known as the MAC with degraded message sets). For both scenarios, new outer bounds on the capacity region are derived, which improve uniformly over the best known outer bounds. In the first scenario, the two corner points of the capacity region as well as the sum rate capacity are established, and it is shown that a single-letter solution is adequate to achieve both the corner points and the sum rate capacity. Furthermore, the full capacity region is characterized in situations in which the sum rate capacity is equal to the capacity of the helper problem. The proof exploits the optimal-transportation idea of Polyanskiy and Wu (which was used previously to establish an outer bound on the capacity region of the interference channel) and the worst-case Gaussian noise result for the case in which the input and the noise are dependent.

cs.IT↗

arXiv2017

Multi-Context Attention for Human Pose Estimation

In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic-consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive fields, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts.

cs.CV↗

arXiv2017

Progressively Diffused Networks for Semantic Image Segmentation

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend to enhance representational power by increasing the depth of architectures and driving the training objective across layers. However, we argue that spatial dependencies in different layers, which generally represent the rich contexts among data elements, are also critical to building deep and discriminative representations. To this end, our PDNs enables to progressively broadcast information over the learned feature maps by inserting a stack of information diffusion layers, each of which exploits multi-dimensional convolutional LSTMs (Long-Short-Term Memory Structures). In each LSTM unit, a special type of atrous filters are designed to capture the short range and long range dependencies from various neighbors to a certain site of the feature map and pass the accumulated information to the next layer. From the extensive experiments on semantic image segmentation benchmarks (e.g., ImageNet Parsing, PASCAL VOC2012 and PASCAL-Part), our framework demonstrates the effectiveness to substantially improve the performances over the popular existing neural network models, and achieves state-of-the-art on ImageNet Parsing for large scale semantic segmentation.

cs.CV↗

arXiv2017

Personalized Classifier Ensemble Pruning Framework for Mobile Crowdsourcing

Ensemble learning has been widely employed by mobile applications, ranging from environmental sensing to activity recognitions. One of the fundamental issue in ensemble learning is the trade-off between classification accuracy and computational costs, which is the goal of ensemble pruning. During crowdsourcing, the centralized aggregator releases ensemble learning models to a large number of mobile participants for task evaluation or as the crowdsourcing learning results, while different participants may seek for different levels of the accuracy-cost trade-off. However, most of existing ensemble pruning approaches consider only one identical level of such trade-off. In this study, we present an efficient ensemble pruning framework for personalized accuracy-cost trade-offs via multi-objective optimization. Specifically, for the commonly used linear-combination style of the trade-off, we provide an objective-mixture optimization to further reduce the number of ensemble candidates. Experimental results show that our framework is highly efficient for personalized ensemble pruning, and achieves much better pruning performance with objective-mixture optimization when compared to state-of-art approaches.

cs.DC↗

arXiv2016

Dislocation Activities at the Martensite Phase Transformation Interface in Metastable Austenitic Stainless Steel: An In-situ TEM Study

Understanding the mechanism of martensitic transformation is of great importance in developing advanced high strength steels, especially TRansformation-Induced Plasticity (TRIP) steels. The TRIP effect leads to enhanced work-hardening rate, postponed onset of necking and excellent formability. In-situ transmission electron microscopy has been performed to systematically investigate the dynamic interactions between dislocations and alpha martensite at microscale. Local stress concentrations, e.g. from notches or dislocation pile-ups, render free edges and grain boundaries favorable nucleation sites for alpha martensite. Its growth leads to partial dislocation emission on two independent slip planes from the hetero-interface when the austenite matrix is initially free of dislocations. The kinematic analysis reveals that activating slip systems on two independent {111} planes of austenite are necessary in accommodating the interfacial mismatch strain. Full dislocation emission is generally observed inside of austenite regions that contain high density of dislocations. In both situations, phase boundary propagation generates large amounts of dislocations entering into the matrix, which renders the total deformation compatible and provide substantial strain hardening of the host phase. These moving dislocation sources enable plastic relaxation and prevent local damage accumulation by intense slipping on the softer side of the interfacial region. Thus, finely dispersed martensite distribution renders plastic deformation more uniform throughout the austenitic matrix, which explains the exceptional combination of strength and ductility of TRIP steels.

cond-mat.mtrl-sci↗