Search Results for author: Chang-Shui Zhang

Found 37 papers, 14 papers with code

Semismooth Newton Algorithm for Efficient Projections onto $\ell_{1, \infty}$-norm Ball

1 code implementation ICML 2020 Dejun Chu, Chang-Shui Zhang, Shiliang Sun, Qing Tao

Structured sparsity-inducing $\ell_{1, \infty}$-norm, as a generalization of the classical $\ell_1$-norm, plays an important role in jointly sparse models which select or remove simultaneously all the variables forming a group.

On Connections between Regularizations for Improving DNN Robustness

no code implementations4 Jul 2020 Yiwen Guo, Long Chen, Yurong Chen, Chang-Shui Zhang

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view.

Adversarial Robustness BIG-bench Machine Learning +1

Road Network Metric Learning for Estimated Time of Arrival

no code implementations24 Jun 2020 Yiwen Sun, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye

To address the data sparsity problem, we propose the Road Network Metric Learning framework for ETA (RNML-ETA).

Metric Learning

Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility

1 code implementation15 Jun 2020 Sen Cui, Weishen Pan, Chang-Shui Zhang, Fei Wang

Bipartite ranking, which aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data, is widely adopted in various applications where sample prioritization is needed.

Fairness

FMA-ETA: Estimating Travel Time Entirely Based on FFN With Attention

no code implementations7 Jun 2020 Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Ziang Yan, Chang-Shui Zhang, Jieping Ye

Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems and becomes a challenging spatial-temporal (ST) data mining task in recent years.

Fusion Recurrent Neural Network

no code implementations7 Jun 2020 Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye

Furthermore, in order to evaluate Fusion RNN's sequence feature extraction capability, we choose a representative data mining task for sequence data, estimated time of arrival (ETA) and present a novel model based on Fusion RNN.

Sparse Coding with Gated Learned ISTA

1 code implementation ICLR 2020 Kailun Wu, Yiwen Guo, Ziang Li, Chang-Shui Zhang

In this paper, we study the learned iterative shrinkage thresholding algorithm (LISTA) for solving sparse coding problems.

Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting

no code implementations23 Apr 2020 Yiwen Sun, Yulu Wang, Kun fu, Zheng Wang, Chang-Shui Zhang, Jieping Ye

Recently, deep learning based methods have achieved promising results by adopting graph convolutional network (GCN) to extract the spatial correlations and recurrent neural network (RNN) to capture the temporal dependencies.

Boosting Semantic Human Matting with Coarse Annotations

1 code implementation CVPR 2020 Jinlin Liu, Yuan YAO, Wendi Hou, Miaomiao Cui, Xuansong Xie, Chang-Shui Zhang, Xian-Sheng Hua

In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.

Image Matting Semantic Segmentation

RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

no code implementations8 Feb 2020 Nan Jiang, Sheng Jin, Zhiyao Duan, Chang-Shui Zhang

We cast this as a reinforcement learning problem, where the generation agent learns a policy to generate a musical note (action) based on previously generated context (state).

Music Generation reinforcement-learning +1

Adversarial Margin Maximization Networks

1 code implementation14 Nov 2019 Ziang Yan, Yiwen Guo, Chang-Shui Zhang

The tremendous recent success of deep neural networks (DNNs) has sparked a surge of interest in understanding their predictive ability.

What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues

1 code implementation IJCNLP 2019 Xintong Yu, Hongming Zhang, Yangqiu Song, Yan Song, Chang-Shui Zhang

To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues.

coreference-resolution Natural Language Understanding

Self-reinforcing Unsupervised Matching

no code implementations23 Aug 2019 Jiang Lu, Lei LI, Chang-Shui Zhang

Remarkable gains in deep learning usually rely on tremendous supervised data.

Continual Learning speech-recognition +1

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks

2 code implementations NeurIPS 2019 Ziang Yan, Yiwen Guo, Chang-Shui Zhang

Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients.

Adversarial Attack

Few Sample Knowledge Distillation for Efficient Network Compression

1 code implementation CVPR 2020 Tianhong Li, Jianguo Li, Zhuang Liu, Chang-Shui Zhang

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high.

Knowledge Distillation Network Pruning +2

Connectionist Temporal Classification with Maximum Entropy Regularization

1 code implementation NeurIPS 2018 Hu Liu, Sheng Jin, Chang-Shui Zhang

Connectionist Temporal Classification (CTC) is an objective function for end-to-end sequence learning, which adopts dynamic programming algorithms to directly learn the mapping between sequences.

Classification General Classification +3

Sparse DNNs with Improved Adversarial Robustness

no code implementations NeurIPS 2018 Yiwen Guo, Chao Zhang, Chang-Shui Zhang, Yurong Chen

Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications.

Adversarial Robustness General Classification

Model-Protected Multi-Task Learning

1 code implementation18 Sep 2018 Jian Liang, Ziqi Liu, Jiayu Zhou, Xiaoqian Jiang, Chang-Shui Zhang, Fei Wang

Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together.

Multi-Task Learning Privacy Preserving

Deep Defense: Training DNNs with Improved Adversarial Robustness

1 code implementation NeurIPS 2018 Ziang Yan, Yiwen Guo, Chang-Shui Zhang

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems.

Adversarial Robustness

Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor

no code implementations24 Dec 2017 Shiliang Sun, Chang-Shui Zhang, Yi Zhang

A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed.

An In-field Automatic Wheat Disease Diagnosis System

no code implementations26 Sep 2017 Jiang Lu, Jie Hu, Guannan Zhao, Fenghua Mei, Chang-Shui Zhang

Crop diseases are responsible for the major production reduction and economic losses in agricultural industry world- wide.

Management Multiple Instance Learning

Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization

no code implementations CVPR 2017 Runpeng Cui, Hu Liu, Chang-Shui Zhang

This work presents a weakly supervised framework with deep neural networks for vision-based continuous sign language recognition, where the ordered gloss labels but no exact temporal locations are available with the video of sign sentence, and the amount of labeled sentences for training is limited.

Sentence Sign Language Recognition

Zero-Shot Learning by Generating Pseudo Feature Representations

no code implementations19 Mar 2017 Jiang Lu, Jin Li, Ziang Yan, Chang-Shui Zhang

Given the dataset of seen classes and side information of unseen classes (e. g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor.

Attribute Novel Concepts +2

Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm

no code implementations28 Feb 2017 Ziang Yan, Jian Liang, Weishen Pan, Jin Li, Chang-Shui Zhang

Object detection when provided image-level labels instead of instance-level labels (i. e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely costly to obtain.

object-detection Object Detection +1

A DNN Framework For Text Image Rectification From Planar Transformations

no code implementations14 Nov 2016 Chengzhe Yan, Jie Hu, Chang-Shui Zhang

In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions.

Neural Network Architecture Optimization through Submodularity and Supermodularity

no code implementations1 Sep 2016 Junqi Jin, Ziang Yan, Kun fu, Nan Jiang, Chang-Shui Zhang

Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time.

Optimizing Recurrent Neural Networks Architectures under Time Constraints

no code implementations29 Aug 2016 Junqi Jin, Ziang Yan, Kun fu, Nan Jiang, Chang-Shui Zhang

A greedy algorithm with bounds is suggested to solve the transformed problem.

Aligning where to see and what to tell: image caption with region-based attention and scene factorization

1 code implementation20 Jun 2015 Junqi Jin, Kun fu, Runpeng Cui, Fei Sha, Chang-Shui Zhang

In this paper, we propose an image caption system that exploits the parallel structures between images and sentences.

Image Captioning

Seeing the Arrow of Time

no code implementations CVPR 2014 Lyndsey C. Pickup, Zheng Pan, Donglai Wei, YiChang Shih, Chang-Shui Zhang, Andrew Zisserman, Bernhard Scholkopf, William T. Freeman

We explore whether we can observe Time's Arrow in a temporal sequence--is it possible to tell whether a video is running forwards or backwards?

General Classification Video Compression

Relaxed Sparse Eigenvalue Conditions for Sparse Estimation via Non-convex Regularized Regression

no code implementations14 Jun 2013 Zheng Pan, Chang-Shui Zhang

Finally, we perform some experiments to show the performance of CD methods on giving AGAS solutions and the degree of weakness of the estimation conditions required by the sharp concave regularizers.

regression

A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems

4 code implementations18 Mar 2013 Pinghua Gong, Chang-Shui Zhang, Zhaosong Lu, Jianhua Huang, Jieping Ye

A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems.

Sparse Learning

Audio Classical Composer Identification by Deep Neural Network

no code implementations15 Jan 2013 Zhen Hu, Kun fu, Chang-Shui Zhang

We think our method is promising even though we test it in a different data set, since our data set is comparable to that in MIREX by size.

Denoising Information Retrieval +2

Multi-Stage Multi-Task Feature Learning

no code implementations NeurIPS 2012 Pinghua Gong, Jieping Ye, Chang-Shui Zhang

In this paper, we propose a non-convex formulation for multi-task sparse feature learning based on a novel regularizer.

Learning Kernels with Radiuses of Minimum Enclosing Balls

no code implementations NeurIPS 2010 Kun Gai, Guangyun Chen, Chang-Shui Zhang

Experiments show that our method significantly outperforms both SVM with the uniform combination of basis kernels and other state-of-art MKL approaches.

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