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 Kai Han

Kai Han

An Image Patch is a Wave: Phase-Aware Vision MLP


Nov 25, 2021
Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang

Figure 1 for An Image Patch is a Wave: Phase-Aware Vision MLP
Figure 2 for An Image Patch is a Wave: Phase-Aware Vision MLP
Figure 3 for An Image Patch is a Wave: Phase-Aware Vision MLP
Figure 4 for An Image Patch is a Wave: Phase-Aware Vision MLP

  Access Paper or Ask Questions

Open-Set Recognition: A Good Closed-Set Classifier is All You Need


Oct 12, 2021
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

Figure 1 for Open-Set Recognition: A Good Closed-Set Classifier is All You Need
Figure 2 for Open-Set Recognition: A Good Closed-Set Classifier is All You Need
Figure 3 for Open-Set Recognition: A Good Closed-Set Classifier is All You Need
Figure 4 for Open-Set Recognition: A Good Closed-Set Classifier is All You Need
* 23 pages, 8 figures 
  Access Paper or Ask Questions

Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images


Oct 11, 2021
Kongming Liang, Kai Han, Xiuli Li, Xiaoqing Cheng, Yiming Li, Yizhou Wang, Yizhou Yu

Figure 1 for Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
Figure 2 for Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
Figure 3 for Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
Figure 4 for Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
* This paper has been accepted by MICCAI2021 
  Access Paper or Ask Questions

Learning Versatile Convolution Filters for Efficient Visual Recognition


Sep 20, 2021
Kai Han, Yunhe Wang, Chang Xu, Chunjing Xu, Enhua Wu, Dacheng Tao

Figure 1 for Learning Versatile Convolution Filters for Efficient Visual Recognition
Figure 2 for Learning Versatile Convolution Filters for Efficient Visual Recognition
Figure 3 for Learning Versatile Convolution Filters for Efficient Visual Recognition
Figure 4 for Learning Versatile Convolution Filters for Efficient Visual Recognition
* Accepted by TPAMI. Extended version of NeurIPS 2018 paper 
  Access Paper or Ask Questions

Hire-MLP: Vision MLP via Hierarchical Rearrangement


Aug 30, 2021
Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, Yunhe Wang

Figure 1 for Hire-MLP: Vision MLP via Hierarchical Rearrangement
Figure 2 for Hire-MLP: Vision MLP via Hierarchical Rearrangement
Figure 3 for Hire-MLP: Vision MLP via Hierarchical Rearrangement
Figure 4 for Hire-MLP: Vision MLP via Hierarchical Rearrangement

  Access Paper or Ask Questions

Greedy Network Enlarging


Aug 04, 2021
Chuanjian Liu, Kai Han, An Xiao, Yiping Deng, Wei Zhang, Chunjing Xu, Yunhe Wang

Figure 1 for Greedy Network Enlarging
Figure 2 for Greedy Network Enlarging
Figure 3 for Greedy Network Enlarging
Figure 4 for Greedy Network Enlarging

  Access Paper or Ask Questions

Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle


Jul 27, 2021
Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu

Figure 1 for Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
Figure 2 for Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
Figure 3 for Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
Figure 4 for Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
* IET Image Processing, code: https://github.com/waterljwant/UGV-KPNet 
  Access Paper or Ask Questions

CMT: Convolutional Neural Networks Meet Vision Transformers


Jul 15, 2021
Jianyuan Guo, Kai Han, Han Wu, Chang Xu, Yehui Tang, Chunjing Xu, Yunhe Wang

Figure 1 for CMT: Convolutional Neural Networks Meet Vision Transformers
Figure 2 for CMT: Convolutional Neural Networks Meet Vision Transformers
Figure 3 for CMT: Convolutional Neural Networks Meet Vision Transformers
Figure 4 for CMT: Convolutional Neural Networks Meet Vision Transformers

  Access Paper or Ask Questions

Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation


Jul 07, 2021
Bingchen Zhao, Kai Han

Figure 1 for Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
Figure 2 for Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
Figure 3 for Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
Figure 4 for Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation

  Access Paper or Ask Questions

Efficient Vision Transformers via Fine-Grained Manifold Distillation


Jul 06, 2021
Ding Jia, Kai Han, Yunhe Wang, Yehui Tang, Jianyuan Guo, Chao Zhang, Dacheng Tao

Figure 1 for Efficient Vision Transformers via Fine-Grained Manifold Distillation
Figure 2 for Efficient Vision Transformers via Fine-Grained Manifold Distillation
Figure 3 for Efficient Vision Transformers via Fine-Grained Manifold Distillation
Figure 4 for Efficient Vision Transformers via Fine-Grained Manifold Distillation

  Access Paper or Ask Questions

Augmented Shortcuts for Vision Transformers


Jun 30, 2021
Yehui Tang, Kai Han, Chang Xu, An Xiao, Yiping Deng, Chao Xu, Yunhe Wang

Figure 1 for Augmented Shortcuts for Vision Transformers
Figure 2 for Augmented Shortcuts for Vision Transformers
Figure 3 for Augmented Shortcuts for Vision Transformers
Figure 4 for Augmented Shortcuts for Vision Transformers

  Access Paper or Ask Questions

AutoNovel: Automatically Discovering and Learning Novel Visual Categories


Jun 29, 2021
Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

Figure 1 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 2 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 3 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 4 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
* TPAMI 2021, code: http://www.robots.ox.ac.uk/~vgg/research/auto_novel/. arXiv admin note: substantial text overlap with arXiv:2002.05714 
  Access Paper or Ask Questions

Post-Training Quantization for Vision Transformer


Jun 27, 2021
Zhenhua Liu, Yunhe Wang, Kai Han, Siwei Ma, Wen Gao

Figure 1 for Post-Training Quantization for Vision Transformer
Figure 2 for Post-Training Quantization for Vision Transformer
Figure 3 for Post-Training Quantization for Vision Transformer
Figure 4 for Post-Training Quantization for Vision Transformer

  Access Paper or Ask Questions

Dynamic Resolution Network


Jun 05, 2021
Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, Yunhe Wang

Figure 1 for Dynamic Resolution Network
Figure 2 for Dynamic Resolution Network
Figure 3 for Dynamic Resolution Network
Figure 4 for Dynamic Resolution Network

  Access Paper or Ask Questions

Patch Slimming for Efficient Vision Transformers


Jun 05, 2021
Yehui Tang, Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chao Xu, Dacheng Tao

Figure 1 for Patch Slimming for Efficient Vision Transformers
Figure 2 for Patch Slimming for Efficient Vision Transformers
Figure 3 for Patch Slimming for Efficient Vision Transformers
Figure 4 for Patch Slimming for Efficient Vision Transformers

  Access Paper or Ask Questions

Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction


May 20, 2021
Kai Han, Kwan-Yee K. Wong, Miaomiao Liu

Figure 1 for Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction
Figure 2 for Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction
Figure 3 for Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction
Figure 4 for Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction
* International Journal of Computer Vision (IJCV) 
  Access Paper or Ask Questions

Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data


Apr 27, 2021
Xuhui Jia, Kai Han, Yukun Zhu, Bradley Green

Figure 1 for Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
Figure 2 for Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
Figure 3 for Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
Figure 4 for Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data

  Access Paper or Ask Questions

Visual Transformer Pruning


Apr 20, 2021
Mingjian Zhu, Kai Han, Yehui Tang, Yunhe Wang

Figure 1 for Visual Transformer Pruning
Figure 2 for Visual Transformer Pruning
Figure 3 for Visual Transformer Pruning
Figure 4 for Visual Transformer Pruning

  Access Paper or Ask Questions

Distilling Object Detectors via Decoupled Features


Mar 26, 2021
Jianyuan Guo, Kai Han, Yunhe Wang, Han Wu, Xinghao Chen, Chunjing Xu, Chang Xu

Figure 1 for Distilling Object Detectors via Decoupled Features
Figure 2 for Distilling Object Detectors via Decoupled Features
Figure 3 for Distilling Object Detectors via Decoupled Features
Figure 4 for Distilling Object Detectors via Decoupled Features
* Accepted in CVPR 2021 
  Access Paper or Ask Questions

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification


Mar 26, 2021
Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, Lei Wang

Figure 1 for Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Figure 2 for Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Figure 3 for Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Figure 4 for Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
* CVPR 2021 
  Access Paper or Ask Questions

Learning Frequency Domain Approximation for Binary Neural Networks


Mar 01, 2021
Yixing Xu, Kai Han, Chang Xu, Yehui Tang, Chunjing Xu, Yunhe Wang

Figure 1 for Learning Frequency Domain Approximation for Binary Neural Networks
Figure 2 for Learning Frequency Domain Approximation for Binary Neural Networks
Figure 3 for Learning Frequency Domain Approximation for Binary Neural Networks
Figure 4 for Learning Frequency Domain Approximation for Binary Neural Networks
* 10 pages, 4 figures 
  Access Paper or Ask Questions

Transformer in Transformer


Feb 27, 2021
Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, Yunhe Wang

Figure 1 for Transformer in Transformer
Figure 2 for Transformer in Transformer
Figure 3 for Transformer in Transformer
Figure 4 for Transformer in Transformer

  Access Paper or Ask Questions

AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence


Feb 03, 2021
Yunhe Wang, Mingqiang Huang, Kai Han, Hanting Chen, Wei Zhang, Chunjing Xu, Dacheng Tao

Figure 1 for AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
Figure 2 for AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
Figure 3 for AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
Figure 4 for AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence

  Access Paper or Ask Questions

A Survey on Visual Transformer


Jan 30, 2021
Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang, Yiman Zhang, Dacheng Tao

Figure 1 for A Survey on Visual Transformer
Figure 2 for A Survey on Visual Transformer
Figure 3 for A Survey on Visual Transformer
Figure 4 for A Survey on Visual Transformer

  Access Paper or Ask Questions

Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera


Jan 23, 2021
Kai Han, Miaomiao Liu, Dirk Schnieders, Kwan-Yee K. Wong

Figure 1 for Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
Figure 2 for Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
Figure 3 for Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
Figure 4 for Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
* IEEE Transactions on Image Processing (TIP). Code available at https://github.com/k-han/mirror 
  Access Paper or Ask Questions

GhostSR: Learning Ghost Features for Efficient Image Super-Resolution


Jan 21, 2021
Ying Nie, Kai Han, Zhenhua Liu, An Xiao, Yiping Deng, Chunjing Xu, Yunhe Wang

Figure 1 for GhostSR: Learning Ghost Features for Efficient Image Super-Resolution
Figure 2 for GhostSR: Learning Ghost Features for Efficient Image Super-Resolution
Figure 3 for GhostSR: Learning Ghost Features for Efficient Image Super-Resolution
Figure 4 for GhostSR: Learning Ghost Features for Efficient Image Super-Resolution

  Access Paper or Ask Questions