Search Results for author: Zhao Zhang

Found 57 papers, 10 papers with code

ClusterQ: Semantic Feature Distribution Alignment for Data-Free Quantization

no code implementations30 Apr 2022 Yangcheng Gao, Zhao Zhang, Richang Hong, Haijun Zhang, Jicong Fan, Shuicheng Yan, Meng Wang

To this end, we propose a new and effective data-free quantization method termed ClusterQ, which utilizes the semantic feature distribution alignment for synthetic data generation.

Data Free Quantization Model Compression +1

Image Harmonization by Matching Regional References

no code implementations10 Apr 2022 Ziyue Zhu, Zhao Zhang, Zheng Lin, Ruiqi Wu, Zhi Chai, Chun-Le Guo

To achieve visual consistency in composite images, recent image harmonization methods typically summarize the appearance pattern of global background and apply it to the global foreground without location discrepancy.

Interactive Style Transfer: All is Your Palette

no code implementations25 Mar 2022 Zheng Lin, Zhao Zhang, Kang-Rui Zhang, Bo Ren, Ming-Ming Cheng

Our IST method can serve as a brush, dip style from anywhere, and then paint to any region of the target content image.

Style Transfer

A Hybrid Physics Machine Learning Approach for Macroscopic Traffic State Estimation

no code implementations1 Feb 2022 Zhao Zhang, Ding Zhao, Xianfeng Terry Yang

Full-field traffic state information (i. e., flow, speed, and density) is critical for the successful operation of Intelligent Transportation Systems (ITS) on freeways.

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

no code implementations27 Dec 2021 Fuwei Zhang, Zhao Zhang, Xiang Ao, Dehong Gao, Fuzhen Zhuang, Yi Wei, Qing He

The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism.

Information Retrieval

Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing

no code implementations24 Nov 2021 Yu Liu, Mingbo Zhao, Zhao Zhang, Haijun Zhang, Shuicheng Yan

Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person.

Geometric Matching Virtual Try-on

Heterogeneous Graph Neural Network with Multi-view Representation Learning

no code implementations31 Aug 2021 Zezhi Shao, Yongjun Xu, Wei Wei, Fei Wang, Zhao Zhang, Feida Zhu

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.

Graph Embedding Link Prediction +2

EGGS: Eigen-Gap Guided Search For Automated Spectral Clustering

no code implementations23 Jul 2021 Jicong Fan, Zhao Zhang, Mingbo Zhao, Yiheng Tu, Haijun Zhang

The main idea is to find the most reliable affinity matrix among a set of candidates given by different AMC methods with different hyperparameters, where the reliability is quantified by the \textit{relative-eigen-gap} of graph Laplacian introduced in this paper.

Image Clustering

KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks

2 code implementations4 Jul 2021 J. Gregory Pauloski, Qi Huang, Lei Huang, Shivaram Venkataraman, Kyle Chard, Ian Foster, Zhao Zhang

Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge faster in deep neural network (DNN) training than stochastic gradient descent (SGD); however, K-FAC's larger memory footprint hinders its applicability to large models.

Many-to-English Machine Translation Tools, Data, and Pretrained Models

2 code implementations ACL 2021 Thamme Gowda, Zhao Zhang, Chris A Mattmann, Jonathan May

While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages.

Machine Translation Transfer Learning +1

Phase transition gravitational waves from pseudo-Nambu-Goldstone dark matter and two Higgs doublets

no code implementations2 Feb 2021 Zhao Zhang, Chengfeng Cai, Xue-Min Jiang, Yi-Lei Tang, Zhao-Huan Yu, Hong-Hao Zhang

We investigate the potential stochastic gravitational waves from first-order electroweak phase transitions in a model with pseudo-Nambu-Goldstone dark matter and two Higgs doublets.

High Energy Physics - Phenomenology Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology

Insight-HXMT observations of Swift J0243.6+6124: the evolution of RMS pulse fractions at super-Eddington luminosity

no code implementations24 Dec 2020 P. J. Wang, L. D. Kong, S. Zhang, Y. P. Chen, S. N. Zhang, J. L. Qu, L. Ji, L. Tao, M. Y. Ge, F. J. Lu, L. Chen, L. M. Song, T. P. Li, Y. P. Xu, X. L. Cao, Y. Chen, C. Z. Liu, Q. C. Bu, C. Cai, Z. Chang, G. Chen, T. X. Chen, Y. B. Chen, W. Cui, W. W. Cui, J. K. Deng, Y. W. Dong, Y. Y. Du, M. X. Fu, G. H. Gao, H. Gao, M. Gao, Y. D. Gu, J. Guan, C. C. Guo, D. W. Han, Y. Huang, J. Huo, S. M. Jia, L. H. Jiang, W. C. Jiang, J. Jin, Y. J. Jin, B. Li, C. K. Li, G. Li, M. S. Li, W. Li, X. Li, X. B. Li, X. F. Li, Y. G. Li, Z. W. Li, X. H. Liang, J. Y. Liao, B. S. Liu, G. Q. Liu, H. W. Liu, X. J. Liu, Y. N. Liu, B. Lu, X. F. Lu, Q. Luo, T. Luo, X. Ma, B. Meng, Y. Nang, J. Y. Nie, G. Ou, N. Sai, R. C. Shang, X. Y. Song, L. Sun, Y. Tan, Y. L. Tuo, C. Wang, G. F. Wang, J. Wang, L. J. Wang, W. S. Wang, Y. S. Wang, X. Y. Wen, B. Y. Wu, B. B. Wu, M. Wu, G. C. Xiao, S. Xiao, S. L. Xiong, J. W. Yang, S. Yang, Yan Ji Yang, Yi Jung Yang, Q. B. Yi, Q. Q. Yin, Y. You, A. M. Zhang, C. M. Zhang, F. Zhang, H. M. Zhang, J. Zhang, T. Zhang, W. C. Zhang, W. Zhang, W. Z. Zhang, Y. F. Zhang, Y. J. Zhang, Y. Zhang, Zhao Zhang, Zhi Zhang, Z. L. Zhang, H. S. Zhao, X. F. Zhao, S. J. Zheng, Y. G. Zheng, D. K. Zhou, J. F. Zhou, Y. X. Zhu, Y. Zhu, R. L. Zhuang

The results show a general trend of the pulse fraction increasing with luminosity and energy at super-critical luminosity.

High Energy Astrophysical Phenomena

Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

no code implementations8 Sep 2020 Yan Zhang, Zhao Zhang, Yang Wang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.

Graph Learning Representation Learning

A Survey on Concept Factorization: From Shallow to Deep Representation Learning

no code implementations31 Jul 2020 Zhao Zhang, Yan Zhang, Mingliang Xu, Li Zhang, Yi Yang, Shuicheng Yan

In this paper, we therefore survey the recent advances on CF methodologies and the potential benchmarks by categorizing and summarizing the current methods.

Representation Learning

Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: Generalized Formulations

no code implementations14 Jul 2020 Yun Yuan, Zhao Zhang, Xianfeng Terry Yang

This novel approach can encode physics models, i. e., classical traffic flow models, into the Gaussian process architecture and so as to regularize the ML training process.

Stochastic Optimization

Convolutional Neural Network Training with Distributed K-FAC

2 code implementations1 Jul 2020 J. Gregory Pauloski, Zhao Zhang, Lei Huang, Weijia Xu, Ian T. Foster

Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales.

Unsupervised Vehicle Re-identification with Progressive Adaptation

no code implementations20 Jun 2020 Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang

For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.

Vehicle Re-Identification

The Limit of the Batch Size

no code implementations15 Jun 2020 Yang You, Yuhui Wang, huan zhang, Zhao Zhang, James Demmel, Cho-Jui Hsieh

For the first time we scale the batch size on ImageNet to at least a magnitude larger than all previous work, and provide detailed studies on the performance of many state-of-the-art optimization schemes under this setting.

Bilateral Attention Network for RGB-D Salient Object Detection

1 code implementation30 Apr 2020 Zhao Zhang, Zheng Lin, Jun Xu, Wenda Jin, Shao-Ping Lu, Deng-Ping Fan

To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task.

RGB-D Salient Object Detection RGB Salient Object Detection +1

Gradient-Induced Co-Saliency Detection

1 code implementation ECCV 2020 Zhao Zhang, Wenda Jin, Jun Xu, Ming-Ming Cheng

Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images.

Co-Salient Object Detection

Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications

no code implementations6 Feb 2020 Yun Yuan, Xianfeng Terry Yang, Zhao Zhang, Shandian Zhe

To address this issue, this study presents a new modeling framework, named physics regularized machine learning (PRML), to encode classical traffic flow models (referred as physical models) into the ML architecture and to regularize the ML training process.

Bayesian Inference Stochastic Optimization

Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network

no code implementations23 Jan 2020 Yanyan Wei, Zhao Zhang, Yang Wang, Haijun Zhang, Mingbo Zhao, Mingliang Xu, Meng Wang

Although supervised deep deraining networks have obtained impressive results on synthetic datasets, they still cannot obtain satisfactory results on real images due to weak generalization of rain removal capacity, i. e., the pre-trained models usually cannot handle new shapes and directions that may lead to over-derained/under-derained results.

Single Image Deraining

Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition

no code implementations23 Jan 2020 Zhao Zhang, Zemin Tang, Yang Wang, Zheng Zhang, Choujun Zhan, ZhengJun Zha, Meng Wang

To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time.

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

no code implementations26 Dec 2019 Jiahuan Ren, Zhao Zhang, Sheng Li, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang

Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient.

Dictionary Learning

Convolutional Dictionary Pair Learning Network for Image Representation Learning

no code implementations17 Dec 2019 Zhao Zhang, Yulin Sun, Yang Wang, Zheng-Jun Zha, Shuicheng Yan, Meng Wang

To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework.

Dictionary Learning Representation Learning

DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking

no code implementations15 Dec 2019 Yanyan Wei, Zhao Zhang, Yang Wang, Mingliang Xu, Yi Yang, Shuicheng Yan, Meng Wang

However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results.

Single Image Deraining Transfer Learning

Compressed DenseNet for Lightweight Character Recognition

no code implementations15 Dec 2019 Zhao Zhang, Zemin Tang, Yang Wang, Haijun Zhang, Shuicheng Yan, Meng Wang

LDB is a convolutional block similarly as dense block, but it can reduce the computation cost and weight size to (1/L, 2/L), compared with original ones, where L is the number of layers in blocks.

Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery

no code implementations13 Dec 2019 Xianzhen Li, Zhao Zhang, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang

In this paper, we explore the deep multi-subspace recovery problem by designing a multilayer architecture for latent LRR.

Representation Learning

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

no code implementations13 Dec 2019 Zhao Zhang, Zemin Tang, Zheng Zhang, Yang Wang, Jie Qin, Meng Wang

But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized.

Deep Self-representative Concept Factorization Network for Representation Learning

no code implementations13 Dec 2019 Yan Zhang, Zhao Zhang, Zheng Zhang, Mingbo Zhao, Li Zhang, Zheng-Jun Zha, Meng Wang

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features.

Representation Learning

Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition

no code implementations1 Dec 2019 Biao Qian, Yang Wang, Zhao Zhang, Richang Hong, Meng Wang, Ling Shao

We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.

Landmark Recognition

Kernelized Multiview Subspace Analysis by Self-weighted Learning

no code implementations23 Nov 2019 Huibing Wang, Yang Wang, Zhao Zhang, Xianping Fu, Zhuo Li, Mingliang Xu, Meng Wang

With the popularity of multimedia technology, information is always represented or transmitted from multiple views.

Dimensionality Reduction Image Retrieval

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning

no code implementations20 Nov 2019 Yulin Sun, Zhao Zhang, Weiming Jiang, Zheng Zhang, Li Zhang, Shuicheng Yan, Meng Wang

In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning.

Representation Learning

Robust Triple-Matrix-Recovery-Based Auto-Weighted Label Propagation for Classification

no code implementations20 Nov 2019 Huan Zhang, Zhao Zhang, Mingbo Zhao, Qiaolin Ye, Min Zhang, Meng Wang

Our method can jointly re-cover the underlying clean data, clean labels and clean weighting spaces by decomposing the original data, predicted soft labels or weights into a clean part plus an error part by fitting noise.

General Classification

Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering

no code implementations2 Sep 2019 Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang

For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates.

A Coarse-to-Fine Multi-stream Hybrid Deraining Network for Single Image Deraining

no code implementations28 Aug 2019 Yanyan Wei, Zhao Zhang, Haijun Zhang, Richang Hong, Meng Wang

To obtain the negative rain streaks during training process more accurately, we present a new module named dual path residual dense block, i. e., Residual path and Dense path.

Single Image Deraining SSIM

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

no code implementations21 Aug 2019 Zhao Zhang, Yulin Sun, Zheng Zhang, Yang Wang, Guangcan Liu, Meng Wang

In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner.

General Classification

Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery

no code implementations21 Aug 2019 Zhao Zhang, Lei Wang, Sheng Li, Yang Wang, Zheng Zhang, Zheng-Jun Zha, Meng Wang

Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part.

Representation Learning

Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation

no code implementations4 Aug 2019 Zhao Zhang, Jiahuan Ren, Sheng Li, Richang Hong, Zheng-Jun Zha, Meng Wang

Leveraging on the Frobenius-norm based latent low-rank representation model, rBDLR jointly learns the coding coefficients and salient features, and improves the results by enhancing the robustness to outliers and errors in given data, preserving local information of salient features adaptively and ensuring the block-diagonal structures of the coefficients.

Representation Learning

Joint Subspace Recovery and Enhanced Locality Driven Robust Flexible Discriminative Dictionary Learning

no code implementations11 Jun 2019 Zhao Zhang, Jiahuan Ren, Weiming Jiang, Zheng Zhang, Richang Hong, Shuicheng Yan, Meng Wang

We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learning (RFDDL).

Dictionary Learning

Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification

no code implementations29 May 2019 Zhao Zhang, Lei Jia, Mingbo Zhao, Guangcan Liu, Meng Wang, Shuicheng Yan

A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space.

General Classification

Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier

no code implementations27 May 2019 Zhao Zhang, Weiming Jiang, Jie Qin, Li Zhang, Fanzhang Li, Min Zhang, Shuicheng Yan

Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers.

Dictionary Learning General Classification

Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering

no code implementations25 May 2019 Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Meng Wang, Shuicheng Yan

RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model.

Image Clustering Representation Learning

Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning

no code implementations25 May 2019 Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin

More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.

Dictionary Learning

Joint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation

no code implementations25 May 2019 Zhao Zhang, Yan Zhang, Guangcan Liu, Jinhui Tang, Shuicheng Yan, Meng Wang

To enrich prior knowledge to enhance the discrimination, RS2ACF clearly uses class information of labeled data and more importantly propagates it to unlabeled data by jointly learning an explicit label indicator for unlabeled data.

Concurrency Protocol Aiming at High Performance of Execution and Replay for Smart Contracts

no code implementations17 May 2019 Shuaifeng Pang, Xiaodong Qi, Zhao Zhang, Cheqing Jin, Aoying Zhou

Although the emergence of the programmable smart contract makes blockchain systems easily embrace a wider range of industrial areas, how to execute smart contracts efficiently becomes a big challenge nowadays.

Databases Distributed, Parallel, and Cluster Computing

Knowledge Graph Embedding with Hierarchical Relation Structure

no code implementations EMNLP 2018 Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He

To this end, in this paper, we extend existing KGE models TransE, TransH and DistMult, to learn knowledge representations by leveraging the information from the HRS.

Information Retrieval Knowledge Base Completion +3

FanStore: Enabling Efficient and Scalable I/O for Distributed Deep Learning

1 code implementation27 Sep 2018 Zhao Zhang, Lei Huang, Uri Manor, Linjing Fang, Gabriele Merlo, Craig Michoski, John Cazes, Niall Gaffney

Our experiments with benchmarks and real applications show that FanStore can scale DL training to 512 compute nodes with over 90\% scaling efficiency.

Distributed, Parallel, and Cluster Computing

Robust Subspace Clustering with Compressed Data

no code implementations30 Mar 2018 Guangcan Liu, Zhao Zhang, Qingshan Liu, Kongkai Xiong

Dimension reduction is widely regarded as an effective way for decreasing the computation, storage and communication loads of data-driven intelligent systems, leading to a growing demand for statistical methods that allow analysis (e. g., clustering) of compressed data.

Dimensionality Reduction

ImageNet Training in Minutes

1 code implementation14 Sep 2017 Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, Kurt Keutzer

If we can make full use of the supercomputer for DNN training, we should be able to finish the 90-epoch ResNet-50 training in one minute.

Cannot find the paper you are looking for? You can Submit a new open access paper.