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 Huan Wang

Huan Wang

College of Informatics, Huazhong Agricultural University

Emerging Paradigms of Neural Network Pruning


Mar 11, 2021
Huan Wang, Can Qin, Yulun Zhang, Yun Fu

Figure 1 for Emerging Paradigms of Neural Network Pruning
Figure 2 for Emerging Paradigms of Neural Network Pruning

  Access Paper or Ask Questions

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games


Feb 23, 2021
Yu Bai, Chi Jin, Huan Wang, Caiming Xiong

Figure 1 for Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
Figure 2 for Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
Figure 3 for Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
Figure 4 for Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

  Access Paper or Ask Questions

Localized Calibration: Metrics and Recalibration


Feb 22, 2021
Rachel Luo, Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai, Shengjia Zhao, Stefano Ermon

Figure 1 for Localized Calibration: Metrics and Recalibration
Figure 2 for Localized Calibration: Metrics and Recalibration
Figure 3 for Localized Calibration: Metrics and Recalibration
Figure 4 for Localized Calibration: Metrics and Recalibration

  Access Paper or Ask Questions

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification


Feb 15, 2021
Yu Bai, Song Mei, Huan Wang, Caiming Xiong

Figure 1 for Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Figure 2 for Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Figure 3 for Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Figure 4 for Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

  Access Paper or Ask Questions

Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss


Feb 03, 2021
Wenhui Lei, Haochen Mei, Zhengwentai Sun, Shan Ye, Ran Gu, Huan Wang, Rui Huang, Shichuan Zhang, Shaoting Zhang, Guotai Wang

Figure 1 for Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
Figure 2 for Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
Figure 3 for Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
Figure 4 for Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
* Accepted by Neurocomputing 
  Access Paper or Ask Questions

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization


Dec 28, 2020
Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras

Figure 1 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 2 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 3 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 4 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
* The last two authors contributed equally 
  Access Paper or Ask Questions

Neural Pruning via Growing Regularization


Dec 16, 2020
Huan Wang, Can Qin, Yulun Zhang, Yun Fu

Figure 1 for Neural Pruning via Growing Regularization
Figure 2 for Neural Pruning via Growing Regularization
Figure 3 for Neural Pruning via Growing Regularization
Figure 4 for Neural Pruning via Growing Regularization

  Access Paper or Ask Questions

An Event Correlation Filtering Method for Fake News Detection


Dec 13, 2020
Hao Li, Huan Wang, Guanghua Liu

Figure 1 for An Event Correlation Filtering Method for Fake News Detection
Figure 2 for An Event Correlation Filtering Method for Fake News Detection
Figure 3 for An Event Correlation Filtering Method for Fake News Detection
* 24 pages, 5 figures, 3 tables 
  Access Paper or Ask Questions

Multi-head Knowledge Distillation for Model Compression


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

Figure 1 for Multi-head Knowledge Distillation for Model Compression
Figure 2 for Multi-head Knowledge Distillation for Model Compression
Figure 3 for Multi-head Knowledge Distillation for Model Compression
Figure 4 for Multi-head Knowledge Distillation for Model Compression
* Copyright: 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 
  Access Paper or Ask Questions

Knowledge Distillation Thrives on Data Augmentation


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

Figure 1 for Knowledge Distillation Thrives on Data Augmentation
Figure 2 for Knowledge Distillation Thrives on Data Augmentation
Figure 3 for Knowledge Distillation Thrives on Data Augmentation
Figure 4 for Knowledge Distillation Thrives on Data Augmentation
* Code will be updated soon 
  Access Paper or Ask Questions

Unsupervised Paraphrase Generation via Dynamic Blocking


Oct 24, 2020
Tong Niu, Semih Yavuz, Yingbo Zhou, Huan Wang, Nitish Shirish Keskar, Caiming Xiong

Figure 1 for Unsupervised Paraphrase Generation via Dynamic Blocking
Figure 2 for Unsupervised Paraphrase Generation via Dynamic Blocking
Figure 3 for Unsupervised Paraphrase Generation via Dynamic Blocking
Figure 4 for Unsupervised Paraphrase Generation via Dynamic Blocking
* 10 pages 
  Access Paper or Ask Questions

How Important is the Train-Validation Split in Meta-Learning?


Oct 12, 2020
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong

Figure 1 for How Important is the Train-Validation Split in Meta-Learning?
Figure 2 for How Important is the Train-Validation Split in Meta-Learning?
Figure 3 for How Important is the Train-Validation Split in Meta-Learning?

  Access Paper or Ask Questions

Towards Understanding Hierarchical Learning: Benefits of Neural Representations


Jun 24, 2020
Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Collaborative Distillation for Ultra-Resolution Universal Style Transfer


Mar 24, 2020
Huan Wang, Yijun Li, Yuehai Wang, Haoji Hu, Ming-Hsuan Yang

Figure 1 for Collaborative Distillation for Ultra-Resolution Universal Style Transfer
Figure 2 for Collaborative Distillation for Ultra-Resolution Universal Style Transfer
Figure 3 for Collaborative Distillation for Ultra-Resolution Universal Style Transfer
Figure 4 for Collaborative Distillation for Ultra-Resolution Universal Style Transfer
* Accepted by CVPR 2020, higher-resolution images than the camera-ready version 
  Access Paper or Ask Questions

MNN: A Universal and Efficient Inference Engine


Feb 27, 2020
Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Bin Zou, Yafeng Yang, Zongyang Cui, Yu Cai, Tianhang Yu, Chengfei Lv, Zhihua Wu

Figure 1 for MNN: A Universal and Efficient Inference Engine
Figure 2 for MNN: A Universal and Efficient Inference Engine
Figure 3 for MNN: A Universal and Efficient Inference Engine
Figure 4 for MNN: A Universal and Efficient Inference Engine
* Accepted by MLSys 2020 
  Access Paper or Ask Questions

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width


Feb 24, 2020
Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher

Figure 1 for Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Figure 2 for Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Figure 3 for Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Figure 4 for Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width

  Access Paper or Ask Questions

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning


Feb 20, 2020
Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio

Figure 1 for Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
Figure 2 for Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
Figure 3 for Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
Figure 4 for Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning

  Access Paper or Ask Questions

Opposite Structure Learning for Semi-supervised Domain Adaptation


Feb 06, 2020
Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu

Figure 1 for Opposite Structure Learning for Semi-supervised Domain Adaptation
Figure 2 for Opposite Structure Learning for Semi-supervised Domain Adaptation
Figure 3 for Opposite Structure Learning for Semi-supervised Domain Adaptation
Figure 4 for Opposite Structure Learning for Semi-supervised Domain Adaptation
* 8 pages without citations 
  Access Paper or Ask Questions

Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models


Nov 09, 2019
Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong

Figure 1 for Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models
Figure 2 for Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models
Figure 3 for Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models
Figure 4 for Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models

  Access Paper or Ask Questions

Global Capacity Measures for Deep ReLU Networks via Path Sampling


Oct 22, 2019
Ryan Theisen, Jason M. Klusowski, Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

Figure 1 for Global Capacity Measures for Deep ReLU Networks via Path Sampling

  Access Paper or Ask Questions

On the Generalization Gap in Reparameterizable Reinforcement Learning


May 29, 2019
Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher

Figure 1 for On the Generalization Gap in Reparameterizable Reinforcement Learning
* Proceedings of the 36 th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019 
  Access Paper or Ask Questions

Triplet Distillation for Deep Face Recognition


May 19, 2019
Yushu Feng, Huan Wang, Daniel T. Yi, Roland Hu

Figure 1 for Triplet Distillation for Deep Face Recognition
Figure 2 for Triplet Distillation for Deep Face Recognition
* 5 pages, 2 tables, accpeted by ICML 2019 ODML-CDNNR Workshop 
  Access Paper or Ask Questions

Structured Pruning for Efficient ConvNets via Incremental Regularization


Nov 20, 2018
Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu

Figure 1 for Structured Pruning for Efficient ConvNets via Incremental Regularization
Figure 2 for Structured Pruning for Efficient ConvNets via Incremental Regularization
Figure 3 for Structured Pruning for Efficient ConvNets via Incremental Regularization
Figure 4 for Structured Pruning for Efficient ConvNets via Incremental Regularization
* Accepted by NIPS 2018 workshop on "Compact Deep Neural Network Representation with Industrial Applications" 
  Access Paper or Ask Questions

Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method


Nov 19, 2018
Yuxin Zhang, Huan Wang, Yang Luo, Roland Hu

Figure 1 for Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Figure 2 for Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Figure 3 for Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Figure 4 for Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
* Accepted by NIPS 2018 Workshop CDNNRIA 
  Access Paper or Ask Questions

Identifying Generalization Properties in Neural Networks


Sep 19, 2018
Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

Figure 1 for Identifying Generalization Properties in Neural Networks
Figure 2 for Identifying Generalization Properties in Neural Networks
Figure 3 for Identifying Generalization Properties in Neural Networks
Figure 4 for Identifying Generalization Properties in Neural Networks
* 23 pages 
  Access Paper or Ask Questions

Structured Probabilistic Pruning for Convolutional Neural Network Acceleration


Sep 10, 2018
Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu

Figure 1 for Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Figure 2 for Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Figure 3 for Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Figure 4 for Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
* Proceedings of the British Machine Vision Conference (BMVC), 2018 
 * CNN model acceleration, 13 pages, 6 figures, accepted by Proceedings of the British Machine Vision Conference (BMVC), 2018 oral 
  Access Paper or Ask Questions

Structured Deep Neural Network Pruning by Varying Regularization Parameters


Apr 25, 2018
Huan Wang, Qiming Zhang, Yuehai Wang, Roland Hu

Figure 1 for Structured Deep Neural Network Pruning by Varying Regularization Parameters
Figure 2 for Structured Deep Neural Network Pruning by Varying Regularization Parameters
Figure 3 for Structured Deep Neural Network Pruning by Varying Regularization Parameters
Figure 4 for Structured Deep Neural Network Pruning by Varying Regularization Parameters
* 7 pages, 3 figures 
  Access Paper or Ask Questions

Exploiting Color Name Space for Salient Object Detection


Mar 27, 2017
Jing Lou, Huan Wang, Longtao Chen, Qingyuan Xia, Wei Zhu, Mingwu Ren

Figure 1 for Exploiting Color Name Space for Salient Object Detection
Figure 2 for Exploiting Color Name Space for Salient Object Detection
Figure 3 for Exploiting Color Name Space for Salient Object Detection
Figure 4 for Exploiting Color Name Space for Salient Object Detection
* 13 pages, 10 figures, 2 tables 
  Access Paper or Ask Questions