arXiv subjects

Zheng Zhang

Publications and source records attributed to Zheng Zhang.

At least 649 records · Page 36Linked to original sources

arXiv2016

A Big-Data Approach to Handle Many Process Variations: Tensor Recovery and Applications

Fabrication process variations are a major source of yield degradation in the nano-scale design of integrated circuits (IC), microelectromechanical systems (MEMS) and photonic circuits. Stochastic spectral methods are a promising technique to quantify the uncertainties caused by process variations. Despite their superior efficiency over Monte Carlo for many design cases, these algorithms suffer from the curse of dimensionality; i.e., their computational cost grows very fast as the number of random parameters increases. In order to solve this challenging problem, this paper presents a high-dimensional uncertainty quantification algorithm from a big-data perspective. Specifically, we show that the huge number of (e.g., $1.5 \times 10^{27}$) simulation samples in standard stochastic collocation can be reduced to a very small one (e.g., $500$) by exploiting some hidden structures of a high-dimensional data array. This idea is formulated as a tensor recovery problem with sparse and low-rank constraints; and it is solved with an alternating minimization approach. Numerical results show that our approach can simulate efficiently some ICs, as well as MEMS and photonic problems with over 50 independent random parameters, whereas the traditional algorithm can only handle several random parameters.

cs.CE↗

arXiv2016

Tensor Computation: A New Framework for High-Dimensional Problems in EDA

Many critical EDA problems suffer from the curse of dimensionality, i.e. the very fast-scaling computational burden produced by large number of parameters and/or unknown variables. This phenomenon may be caused by multiple spatial or temporal factors (e.g. 3-D field solvers discretizations and multi-rate circuit simulation), nonlinearity of devices and circuits, large number of design or optimization parameters (e.g. full-chip routing/placement and circuit sizing), or extensive process variations (e.g. variability/reliability analysis and design for manufacturability). The computational challenges generated by such high dimensional problems are generally hard to handle efficiently with traditional EDA core algorithms that are based on matrix and vector computation. This paper presents "tensor computation" as an alternative general framework for the development of efficient EDA algorithms and tools. A tensor is a high-dimensional generalization of a matrix and a vector, and is a natural choice for both storing and solving efficiently high-dimensional EDA problems. This paper gives a basic tutorial on tensors, demonstrates some recent examples of EDA applications (e.g., nonlinear circuit modeling and high-dimensional uncertainty quantification), and suggests further open EDA problems where the use of tensor computation could be of advantage.

math.NA↗

arXiv2016

Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study

It is well known that clothing fashion is a distinctive and often habitual trend in the style in which a person dresses. Clothing fashions are usually expressed with visual stimuli such as style, color, and texture. However, it is not clear which visual stimulus places higher/lower influence on the updating of clothing fashion. In this study, computer vision and machine learning techniques are employed to analyze the influence of different visual stimuli on clothing-fashion updates. Specifically, a classification-based model is proposed to quantify the influence of different visual stimuli, in which each visual stimulus's influence is quantified by its corresponding accuracy in fashion classification. Experimental results demonstrate that, on clothing-fashion updates, the style holds a higher influence than the color, and the color holds a higher influence than the texture.

cs.CV↗

arXiv2016

Learning Word Embeddings from Intrinsic and Extrinsic Views

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be learned based on only context. Moreover, it is also difficult to learn the representation of the rare words due to data sparsity problem. In this work, we address these issues by learning the representations of words by integrating their intrinsic (descriptive) and extrinsic (contextual) information. To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries,Wiki link prediction, and document classification. Experiment results show that our model is powerful in both word and document modeling.

cs.CL↗

arXiv2016

Local Multiple Directional Pattern of Palmprint Image

Lines are the most essential and discriminative features of palmprint images, which motivate researches to propose various line direction based methods for palmprint recognition. Conventional methods usually capture the only one of the most dominant direction of palmprint images. However, a number of points in palmprint images have double or even more than two dominant directions because of a plenty of crossing lines of palmprint images. In this paper, we propose a local multiple directional pattern (LMDP) to effectively characterize the multiple direction features of palmprint images. LMDP can not only exactly denote the number and positions of dominant directions but also effectively reflect the confidence of each dominant direction. Then, a simple and effective coding scheme is designed to represent the LMDP and a block-wise LMDP descriptor is used as the feature space of palmprint images in palmprint recognition. Extensive experimental results demonstrate the superiority of the LMDP over the conventional powerful descriptors and the state-of-the-art direction based methods in palmprint recognition.

cs.CV↗

arXiv2016

Natural Scene Character Recognition Using Robust PCA and Sparse Representation

Natural scene character recognition is challenging due to the cluttered background, which is hard to separate from text. In this paper, we propose a novel method for robust scene character recognition. Specifically, we first use robust principal component analysis (PCA) to denoise character image by recovering the missing low-rank component and filtering out the sparse noise term, and then use a simple Histogram of oriented Gradient (HOG) to perform image feature extraction, and finally, use a sparse representation based classifier for recognition. In experiments on four public datasets, namely the Char74K dataset, ICADAR 2003 robust reading dataset, Street View Text (SVT) dataset and IIIT5K-word dataset, our method was demonstrated to be competitive with the state-of-the-art methods.

cs.CV↗

arXiv2016

Multi-Oriented Text Detection with Fully Convolutional Networks

In this paper, we propose a novel approach for text detec- tion in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine pro- cedure. First, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holistic manner. Then, text line hypotheses are estimated by combining the salient map and character components. Fi- nally, another FCN classifier is used to predict the centroid of each character, in order to remove the false hypotheses. The framework is general for handling text in multiple ori- entations, languages and fonts. The proposed method con- sistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, ICDAR2015 and ICDAR2013.

cs.CV↗

arXiv2016

A Big-Data Approach to Handle Process Variations: Uncertainty Quantification by Tensor Recovery

Stochastic spectral methods have become a popular technique to quantify the uncertainties of nano-scale devices and circuits. They are much more efficient than Monte Carlo for certain design cases with a small number of random parameters. However, their computational cost significantly increases as the number of random parameters increases. This paper presents a big-data approach to solve high-dimensional uncertainty quantification problems. Specifically, we simulate integrated circuits and MEMS at only a small number of quadrature samples, then, a huge number of (e.g., $1.5 \times 10^{27}$) solution samples are estimated from the available small-size (e.g., $500$) solution samples via a low-rank and tensor-recovery method. Numerical results show that our algorithm can easily extend the applicability of tensor-product stochastic collocation to IC and MEMS problems with over 50 random parameters, whereas the traditional algorithm can only handle several random parameters.

cs.CE↗

arXiv2016

A survey of sparse representation: algorithms and applications

Sparse representation has attracted much attention from researchers in fields of signal processing, image processing, computer vision and pattern recognition. Sparse representation also has a good reputation in both theoretical research and practical applications. Many different algorithms have been proposed for sparse representation. The main purpose of this article is to provide a comprehensive study and an updated review on sparse representation and to supply a guidance for researchers. The taxonomy of sparse representation methods can be studied from various viewpoints. For example, in terms of different norm minimizations used in sparsity constraints, the methods can be roughly categorized into five groups: sparse representation with $l_0$-norm minimization, sparse representation with $l_p$-norm (0$<$p$<$1) minimization, sparse representation with $l_1$-norm minimization and sparse representation with $l_{2,1}$-norm minimization. In this paper, a comprehensive overview of sparse representation is provided. The available sparse representation algorithms can also be empirically categorized into four groups: greedy strategy approximation, constrained optimization, proximity algorithm-based optimization, and homotopy algorithm-based sparse representation. The rationales of different algorithms in each category are analyzed and a wide range of sparse representation applications are summarized, which could sufficiently reveal the potential nature of the sparse representation theory. Specifically, an experimentally comparative study of these sparse representation algorithms was presented. The Matlab code used in this paper can be available at: http://www.yongxu.org/lunwen.html.

cs.CV↗

arXiv2016

A Bayesian Approach for Parameter Estimation with Uncertainty for Dynamic Power Systems

We address the problem of estimating the uncertainty in the solution of power grid inverse problems within the framework of Bayesian inference. We investigate two approaches, an adjoint-based method and a stochastic spectral method. These methods are used to estimate the maximum a posteriori point of the parameters and their variance, which quantifies their uncertainty. Within this framework we estimate several parameters of the dynamic power system, such as generator inertias, which are not quantifiable in steady-state models. We illustrate the performance of these approaches on a 9-bus power grid example and analyze the dependence on measurement frequency, estimation horizon, perturbation size, and measurement noise. We assess the computational efficiency, and discuss the expected performance when these methods are applied to large systems.

math.OC↗

arXiv2015

Learning to Point and Count

This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock. Different from the traditional detection problem, the goal is to discover key salient points as a way to localize and count the number of objects simultaneously. We propose two alternatives, one that counts first and then point, and another that works the other way around. Fundamentally, they pivot around whether we solve "what" or "where" first. We evaluate their performance on dataset that contains multiple instances of the same class, demonstrating the potentials and their synergies. The experiences derive a few important insights that explains why this is a much harder problem than classification, including strong data bias and the inability to deal with object scales robustly in state-of-art convolutional neural networks.

cs.CV↗

arXiv2015

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

MXNet is a multi-language machine learning (ML) library to ease the development of ML algorithms, especially for deep neural networks. Embedded in the host language, it blends declarative symbolic expression with imperative tensor computation. It offers auto differentiation to derive gradients. MXNet is computation and memory efficient and runs on various heterogeneous systems, ranging from mobile devices to distributed GPU clusters. This paper describes both the API design and the system implementation of MXNet, and explains how embedding of both symbolic expression and tensor operation is handled in a unified fashion. Our preliminary experiments reveal promising results on large scale deep neural network applications using multiple GPU machines.

cs.DC↗

arXiv2015

First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks

In this paper, we propose and study a novel visual object tracking approach based on convolutional networks and recurrent networks. The proposed approach is distinct from the existing approaches to visual object tracking, such as filtering-based ones and tracking-by-detection ones, in the sense that the tracking system is explicitly trained off-line to track anonymous objects in a noisy environment. The proposed visual tracking model is end-to-end trainable, minimizing any adversarial effect from mismatches in object representation and between the true underlying dynamics and learning dynamics. We empirically show that the proposed tracking approach works well in various scenarios by generating artificial video sequences with varying conditions; the number of objects, amount of noise and the match between the training shapes and test shapes.

cs.CV↗

arXiv2015

Probabilistic Power Flow Computation via Low-Rank and Sparse Tensor Recovery

This paper presents a tensor-recovery method to solve probabilistic power flow problems. Our approach generates a high-dimensional and sparse generalized polynomial-chaos expansion that provides useful statistical information. The result can also speed up other essential routines in power systems (e.g., stochastic planning, operations and controls). Instead of simulating a power flow equation at all quadrature points, our approach only simulates an extremely small subset of samples. We suggest a model to exploit the underlying low-rank and sparse structure of high-dimensional simulation data arrays, making our technique applicable to power systems with many random parameters. We also present a numerical method to solve the resulting nonlinear optimization problem. Our algorithm is implemented in MATLAB and is verified by several benchmarks in MATPOWER $5.1$. Accurate results are obtained for power systems with up to $50$ independent random parameters, with a speedup factor up to $9\times 10^{20}$.

cs.CE↗

arXiv2015

Capillary rupture of suspended polymer concentric rings

We present the first experimental study on the simultaneous capillary instability amongst viscous concentric rings suspended atop an immiscible medium. The rings ruptured upon annealing, with three types of phase correlation between neighboring rings. In the case of weak substrate confinement, the rings ruptured independently when they were sparsely distanced, but via an out-of-phase mode when packed closer. If the substrate confinement was strong, the rings would rupture via an in-phase mode, resulting in radially aligned droplets. The concentric ring geometry caused a competition between the phase correlation of neighboring rings and the kinetically favorable wavelength, yielding an intriguing, recursive surface pattern. This frustrated pattern formation behavior was accounted for by a scaling analysis.

cond-mat.soft↗

arXiv2014

Scale-Invariant Convolutional Neural Networks

Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited. The popular practise is making the model bigger first, and then train it with data augmentation using extensive scale-jittering. In this paper, we propose a scaleinvariant convolutional neural network (SiCNN), a modeldesigned to incorporate multi-scale feature exaction and classification into the network structure. SiCNN uses a multi-column architecture, with each column focusing on a particular scale. Unlike previous multi-column strategies, these columns share the same set of filter parameters by a scale transformation among them. This design deals with scale variation without blowing up the model size. Experimental results show that SiCNN detects features at various scales, and the classification result exhibits strong robustness against object scale variations.

cs.CV↗

arXiv2014

The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification

Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification systems follow the pipeline of finding foreground object or object parts (where) to extract discriminative features (what). In this paper, we propose to apply visual attention to fine-grained classification task using deep neural network. Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts. We combine these attentions to train domain-specific deep nets, then use it to improve both the what and where aspects. Importantly, we avoid using expensive annotations like bounding box or part information from end-to-end. The weak supervision constraint makes our work easier to generalize. We have verified the effectiveness of the method on the subsets of ILSVRC2012 dataset and CUB200_2011 dataset. Our pipeline delivered significant improvements and achieved the best accuracy under the weakest supervision condition. The performance is competitive against other methods that rely on additional annotations.

cs.CV↗

arXiv2014

Attentional Neural Network: Feature Selection Using Cognitive Feedback

Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult segmentation problems. Our system is modular and extensible. It is also easy to train and cheap to run, and yet can accommodate complex behaviors. We obtain classification accuracy better than or competitive with state of art results on the MNIST variation dataset, and successfully disentangle overlaid digits with high success rates. We view such a general purpose framework as an essential foundation for a larger system emulating the cognitive abilities of the whole brain.

cs.CV↗