Yawei Li (李亚伟)



profile pic

Ph.D Candidate at Computer Vision Lab, ETH Zürich.

Find Out More!

Biography


I am currently a Ph.D student at Computer Vision Lab supervised by Prof. Luc Van Gool. I am also co-supervised by Dr. Radu Timofte. My research interests include efficient neural network design, neural network compression and acceleration, image restoration, and graph neural networks. Specifically, I developed filter basis learning and pruning methods for network compression and acceleration. During my study, I am fortunate to work with a couple of brilliant senior researchers including Dr. Shuhang Gu, Dr. Kai Zhang, Dr. Martin Danelljan, Dr. Wen Li from the Computer Vision Lab and Dr. Vagia Tsiminaki, Dr. Zhaopeng Cui from the Computer Vision and Geometry Group led by Prof. Marc Pollefeys.

News


  • 2021/04. Our work on vision transformers is available on arXiv! Check the LocalViT paper here.
  • 2021/04. Our work on efficient graph convolutional networks is available on arXiv! Check the paper here.
  • 2021/03. Three papers are accepted by CVPR 2021! Check the papers here. The Heterogeneity Hypothesis. DASR. MOCDA.
  • 2020/12. I'm going to serve as as a Senior PC member for IJCAI 2021.
  • 2020/09. DPIR paper is online. This is collaboration with Kai Zhang. Check the paper here.
  • 2020/08. Code of DHP is available. Check it here.
  • 2020/07. DHP paper is accepted by ECCV2020!
  • 2020/07. The Heterogeneity Hypothesis paper is online now. Check it on Arxiv.
  • 2020/04. DASR paper is online (Arxiv).
  • 2020/03. DHP paper is online (Arxiv).
  • 2020/02. One paper accepted by CVPR2020.
  • 2019/07. One paper accepted by ICCV2019.
  • 2019/07. I won the best poster presentation at ICVSS.
  • 2019/02. One paper accepted by CVPR2019.

Research


Preprints

localvit

Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Luc Van Gool
ArXiv, 2021.
[Paper] [GitHub Repository]

efficient_gcn

Towards Efficient Graph Convolutional Networks for Point Cloud Handling

Yawei Li, He Chen, Zhaopeng Cui, Radu Timofte, Marc Pollefeys, Gregory Chirikjian, Luc Van Gool
ArXiv, 2021.
[Paper] [GitHub Repository]

DPIR

Plug-and-Play Image Restoration with Deep Denoiser Prior

Kai Zhang, Yawei Li, Wangmeng Zuo, Lei Zhang, Luc Van Gool, and Radu Timofte
ArXiv, 2020.
[Paper] [GitHub Repository]

Selected Publications

Heterogeneity Hypothesis

The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture

Yawei Li, Wen Li, Martin Danelljan, Kai Zhang, Shuhang Gu, Luc Van Gool, and Radu Timofte
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper] [GitHub Repository]

DASR 

Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training

Yunxuan Wei, Shuhang Gu, Yawei Li, Longcun Jin
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper] [GitHub Repository]

DASR 

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Rui Gong, Yuhua Chen, Danda Pani Paudel, Yawei Li, Ajad Chhatkuli, Wen Li, Dengxin Dai, Luc Van Gool
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper]

DHP 

DHP: Differentiable Meta Pruning via HyperNetworks

Yawei Li, Shuhang Gu, Kai Zhang, Luc Van Gool, and Radu Timofte
European Conference on Computer Vision and Pattern Recognition (ECCV), 2020.
[Paper] [GitHub Repository] [Slides] [Video] [Video in Chinese]

AIM2020_efficient_sr 

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

Kai Zhang, Martin Danelljan, Yawei Li, Radu Timofte, and others
European Conference on Computer Vision and Pattern Recognition Workshops (ECCVW), 2020.
[Paper] [GitHub Repository]

Group Sparsity 

Group sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Yawei Li, Shuhang Gu, Christoph Mayer, Luc Van Gool, and Radu Timofte
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[Paper] [GitHub Repository]

Filter Basis 

Learning filter basis for convolutional neural network compression

Yawei Li, Shuhang Gu, Luc Van Gool, and Radu Timofte
IEEE International Conference on Computer Vision (ICCV) , 2019.
[Paper] [GitHub Repository]

SGN 

Self-guided network for fast image denoising

Shuhang Gu, Yawei Li, Luc Van Gool, and Radu Timofte
IEEE International Conference on Computer Vision (ICCV), 2019.
[Paper] [GitHub Repository]

3D Appearance SR 

3D appearance super-resolution with deep learning

Yawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, and Luc van Gool
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Paper] [GitHub Repository]

CARN 

CARN: Convolutional anchored regression network for fast and accurate single image super-resolution

Yawei Li, Eirikur Agustsson, Shuhang Gu, Radu Timofte, and Luc Van Gool
European Conference on Computer Vision Workshop (ECCVW), 2018.
[Paper] [GitHub Repository]

ACMMM 

Multiview Video Super-Resolution via Information Extraction and Merging

Yawei Li, Xiaofeng Li, Zhizhong Fu, and Wenli Zhong
ACM International Conference on Multimedia (ACM MM), 2016.
[Paper]

Services


Master Student Supervision

  • Huseyin Ziya Imamoglu, 11/2020-present
  • Silvio Paganucci, 2019-2020

Outstanding Reviewer

  • Asian Conference on Computer Vision (ACCV), 2020

Senior Program Committe (SPC) Member

  • International Joint Conference on Artificial Intelligence (IJCAI), 2021

Conference Reviewer

  • Computer Vision and Pattern Recognition (CVPR)
  • International Conference on Computer Vision (ICCV)
  • Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • ACM International Conference on Multimedia (ACM MM)
  • Asian Conference on Computer Vision (ACCV)
  • Winter Conference on Applications of Computer Vision (WACV)
  • Pacific Graphics

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • IEEE Transactions on Image Processing
  • International Journal of Intelligent Systems
  • Neurocomputing
  • Journal of Systems Architecture
  • PLOS ONE

Teaching Assisstantship

  • 2020 Fall, 227-0085-11L: Deep Learning for Image Manipulation. Lecturers: Luc Van Gool.
  • 2019 Fall, 263-5902-00L: Computer Vision. Lecturers: Marc Pollefeys, Vittorio Ferrari Luc Van Gool
  • 2018 Fall, 263-5902-00L: Computer Vision. Lecturers: Marc Pollefeys, Vittorio Ferrari Luc Van Gool
  • 2017 Fall, 263-5902-00L: Computer Vision. Lecturers: Luc Van Gool, Vittorio Ferrari, Andreas Geiger

Yawei Li © 2020. All rights reserved. Powered by Bootstrap.