Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Zhe Li

Zhe Li

Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention


Jul 20, 2020
Zhe Li, Lianwen Jin, Songxuan Lai, Yecheng Zhu

Figure 1 for Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
Figure 2 for Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
Figure 3 for Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
Figure 4 for Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
* Accepted to appear in ICFHR 2020 
  Access Paper or Ask Questions

Joint Multi-Dimension Pruning


May 18, 2020
Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun

Figure 1 for Joint Multi-Dimension Pruning
Figure 2 for Joint Multi-Dimension Pruning
Figure 3 for Joint Multi-Dimension Pruning
Figure 4 for Joint Multi-Dimension Pruning

  Access Paper or Ask Questions

Robust 3D Self-portraits in Seconds


Apr 06, 2020
Zhe Li, Tao Yu, Chuanyu Pan, Zerong Zheng, Yebin Liu

Figure 1 for Robust 3D Self-portraits in Seconds
Figure 2 for Robust 3D Self-portraits in Seconds
Figure 3 for Robust 3D Self-portraits in Seconds
Figure 4 for Robust 3D Self-portraits in Seconds
* CVPR 2020, oral 
  Access Paper or Ask Questions

RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies


Mar 07, 2020
Zhe Li, Chunhua Sun, Chunli Liu, Xiayu Chen, Meng Wang, Yezheng Liu

Figure 1 for RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
Figure 2 for RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
Figure 3 for RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
Figure 4 for RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies

  Access Paper or Ask Questions

Long Short-Term Sample Distillation


Mar 02, 2020
Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi

Figure 1 for Long Short-Term Sample Distillation
Figure 2 for Long Short-Term Sample Distillation
Figure 3 for Long Short-Term Sample Distillation
Figure 4 for Long Short-Term Sample Distillation
* published as a conference paper at AAAI 2020 
  Access Paper or Ask Questions

Learning From Brains How to Regularize Machines


Nov 11, 2019
Zhe Li, Wieland Brendel, Edgar Y. Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian H. Sinz, Xaq Pitkow, Andreas S. Tolias

Figure 1 for Learning From Brains How to Regularize Machines
Figure 2 for Learning From Brains How to Regularize Machines
Figure 3 for Learning From Brains How to Regularize Machines
Figure 4 for Learning From Brains How to Regularize Machines
* 14 pages, 7 figures, NeurIPS 2019 
  Access Paper or Ask Questions

Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation


Apr 12, 2019
Yuyin Zhou, Zhe Li, Song Bai, Chong Wang, Xinlei Chen, Mei Han, Elliot Fishman, Alan Yuille

Figure 1 for Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Figure 2 for Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Figure 3 for Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Figure 4 for Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
* Tech Report 
  Access Paper or Ask Questions

CircConv: A Structured Convolution with Low Complexity


Feb 28, 2019
Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan

Figure 1 for CircConv: A Structured Convolution with Low Complexity
Figure 2 for CircConv: A Structured Convolution with Low Complexity
Figure 3 for CircConv: A Structured Convolution with Low Complexity
Figure 4 for CircConv: A Structured Convolution with Low Complexity
* Published in AAAI 2019 
  Access Paper or Ask Questions

E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs


Dec 12, 2018
Zhe Li, Caiwen Ding, Siyue Wang, Wujie Wen, Youwei Zhuo, Chang Liu, Qinru Qiu, Wenyao Xu, Xue Lin, Xuehai Qian, Yanzhi Wang

Figure 1 for E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
Figure 2 for E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
Figure 3 for E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
Figure 4 for E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
* In The 25th International Symposium on High-Performance Computer Architecture (HPCA 2019) 
  Access Paper or Ask Questions

Generative Adversarial Active Learning for Unsupervised Outlier Detection


Sep 28, 2018
Yezheng Liu, Zhe Li, Chong Zhou, Yuanchun Jiang, Jianshan Sun, Meng Wang, Xiangnan He

Figure 1 for Generative Adversarial Active Learning for Unsupervised Outlier Detection
Figure 2 for Generative Adversarial Active Learning for Unsupervised Outlier Detection
Figure 3 for Generative Adversarial Active Learning for Unsupervised Outlier Detection
Figure 4 for Generative Adversarial Active Learning for Unsupervised Outlier Detection
* submitted to IEEE Transactions on Knowledge and Data Engineering 
  Access Paper or Ask Questions

A Unified Analysis of Stochastic Momentum Methods for Deep Learning


Aug 30, 2018
Yan Yan, Tianbao Yang, Zhe Li, Qihang Lin, Yi Yang

Figure 1 for A Unified Analysis of Stochastic Momentum Methods for Deep Learning
Figure 2 for A Unified Analysis of Stochastic Momentum Methods for Deep Learning
Figure 3 for A Unified Analysis of Stochastic Momentum Methods for Deep Learning
* In IJCAI, pp. 2955-2961. 2018 
 * Previous Technical Report: arXiv:1604.03257 
  Access Paper or Ask Questions

C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing


Aug 02, 2018
Zhe Li, Xiaolong Ma, Hongjia Li, Qiyuan An, Aditya Singh Rathore, Qinru Qiu, Wenyao Xu, Yanzhi Wang

Figure 1 for C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
Figure 2 for C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
Figure 3 for C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
Figure 4 for C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
* The paper contains error, and the project is suspended, the results will be not updated in the near future, withdraw is better option than replace 
  Access Paper or Ask Questions

Thoracic Disease Identification and Localization with Limited Supervision


Jun 20, 2018
Zhe Li, Chong Wang, Mei Han, Yuan Xue, Wei Wei, Li-Jia Li, Li Fei-Fei

Figure 1 for Thoracic Disease Identification and Localization with Limited Supervision
Figure 2 for Thoracic Disease Identification and Localization with Limited Supervision
Figure 3 for Thoracic Disease Identification and Localization with Limited Supervision
Figure 4 for Thoracic Disease Identification and Localization with Limited Supervision
* Conference on Computer Vision and Pattern Recognition 2018 (CVPR 2018). V1: CVPR submission; V2: +supplementary; V3: CVPR camera-ready; V4: correction, update reference baseline results according to their latest post; V5: minor correction; V6: Identification results using NIH data splits and various image models 
  Access Paper or Ask Questions

EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching


Jun 05, 2018
Jian Ren, Zhe Li, Jianchao Yang, Ning Xu, Tianbao Yang, David J. Foran

Figure 1 for EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching
Figure 2 for EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching
Figure 3 for EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching
Figure 4 for EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching

  Access Paper or Ask Questions

An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints


Jun 03, 2018
Zhe Li, Xuehan Xiong, Zhou Ren, Ning Zhang, Xiaoyu Wang, Tianbao Yang

Figure 1 for An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
Figure 2 for An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
Figure 3 for An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
Figure 4 for An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints

  Access Paper or Ask Questions

Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing


May 10, 2018
Zhe Li, Ji Li, Ao Ren, Caiwen Ding, Jeffrey Draper, Qinru Qiu, Bo Yuan, Yanzhi Wang

Figure 1 for Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
Figure 2 for Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
Figure 3 for Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
Figure 4 for Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
* Accepted by IEEE Computer Society Annual Symposium on VLSI 2018 
  Access Paper or Ask Questions

Learning Topics using Semantic Locality


Apr 11, 2018
Ziyi Zhao, Krittaphat Pugdeethosapol, Sheng Lin, Zhe Li, Caiwen Ding, Yanzhi Wang, Qinru Qiu

Figure 1 for Learning Topics using Semantic Locality
Figure 2 for Learning Topics using Semantic Locality
Figure 3 for Learning Topics using Semantic Locality
Figure 4 for Learning Topics using Semantic Locality
* International Conference of Pattern Recognition (ICPR) in 2018 
  Access Paper or Ask Questions

Efficient Recurrent Neural Networks using Structured Matrices in FPGAs


Mar 22, 2018
Zhe Li, Shuo Wang, Caiwen Ding, Qinru Qiu, Yanzhi Wang, Yun Liang

Figure 1 for Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
Figure 2 for Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
* To appear in International Conference on Learning Representations 2018 Workshop Track 
  Access Paper or Ask Questions

Image Dataset for Visual Objects Classification in 3D Printing


Mar 22, 2018
Hongjia Li, Xiaolong Ma, Aditya Singh Rathore, Zhe Li, Qiyuan An, Chen Song, Wenyao Xu, Yanzhi Wang

Figure 1 for Image Dataset for Visual Objects Classification in 3D Printing
Figure 2 for Image Dataset for Visual Objects Classification in 3D Printing
Figure 3 for Image Dataset for Visual Objects Classification in 3D Printing
* It is not accepted and the work needed major reversion and improvement 
  Access Paper or Ask Questions

C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs


Mar 14, 2018
Shuo Wang, Zhe Li, Caiwen Ding, Bo Yuan, Yanzhi Wang, Qinru Qiu, Yun Liang

Figure 1 for C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
Figure 2 for C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
Figure 3 for C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
Figure 4 for C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
* Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays 
  Access Paper or Ask Questions

A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection


Feb 25, 2018
Kun Hu, Zhe Li, Ying Liu, Luyin Cheng, Qi Yang, Yan Li

Figure 1 for A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
Figure 2 for A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
Figure 3 for A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
Figure 4 for A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
* 14 pages, 6 Figures 
  Access Paper or Ask Questions

Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework


Feb 18, 2018
Yanzhi Wang, Caiwen Ding, Zhe Li, Geng Yuan, Siyu Liao, Xiaolong Ma, Bo Yuan, Xuehai Qian, Jian Tang, Qinru Qiu, Xue Lin

Figure 1 for Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Figure 2 for Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Figure 3 for Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Figure 4 for Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
* 6 figures, AAAI Conference on Artificial Intelligence, 2018 
  Access Paper or Ask Questions

An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing


Feb 03, 2018
Xiaolong Ma, Yipeng Zhang, Geng Yuan, Ao Ren, Zhe Li, Jie Han, Jingtong Hu, Yanzhi Wang

Figure 1 for An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
Figure 2 for An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
Figure 3 for An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
Figure 4 for An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing

  Access Paper or Ask Questions

Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network


Nov 22, 2017
Fangzhou Liao, Ming Liang, Zhe Li, Xiaolin Hu, Sen Song

Figure 1 for Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
Figure 2 for Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
Figure 3 for Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
Figure 4 for Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
* 12 pages, 9 figures 
  Access Paper or Ask Questions

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank


Sep 22, 2017
Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Figure 1 for Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Figure 2 for Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
* 13 pages, 1 figure 
  Access Paper or Ask Questions

A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer


Sep 09, 2017
Tianbao Yang, Zhe Li, Lijun Zhang


  Access Paper or Ask Questions

CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices


Aug 29, 2017
Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yipeng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan

Figure 1 for CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
Figure 2 for CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
Figure 3 for CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
Figure 4 for CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
* 14 pages, 15 Figures, conference 
  Access Paper or Ask Questions

A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning


Aug 11, 2017
Ning Liu, Zhe Li, Zhiyuan Xu, Jielong Xu, Sheng Lin, Qinru Qiu, Jian Tang, Yanzhi Wang

Figure 1 for A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Figure 2 for A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Figure 3 for A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Figure 4 for A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
* accepted by 37th IEEE International Conference on Distributed Computing (ICDCS 2017) 
  Access Paper or Ask Questions

SEP-Nets: Small and Effective Pattern Networks


Jun 13, 2017
Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang

Figure 1 for SEP-Nets: Small and Effective Pattern Networks
Figure 2 for SEP-Nets: Small and Effective Pattern Networks
Figure 3 for SEP-Nets: Small and Effective Pattern Networks
Figure 4 for SEP-Nets: Small and Effective Pattern Networks

  Access Paper or Ask Questions

Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks


Mar 12, 2017
Ji Li, Zihao Yuan, Zhe Li, Caiwen Ding, Ao Ren, Qinru Qiu, Jeffrey Draper, Yanzhi Wang

Figure 1 for Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
Figure 2 for Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
Figure 3 for Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
Figure 4 for Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
* This paper is accepted by 2017 International Joint Conference on Neural Networks (IJCNN) 
  Access Paper or Ask Questions