Picture for Chao-Yuan Wu

Chao-Yuan Wu

Reversible Vision Transformers

Feb 09, 2023
Karttikeya Mangalam, Haoqi Fan, Yanghao Li, Chao-Yuan Wu, Bo Xiong, Christoph Feichtenhofer, Jitendra Malik

Figure 1 for Reversible Vision Transformers

Figure 2 for Reversible Vision Transformers

Figure 3 for Reversible Vision Transformers

Figure 4 for Reversible Vision Transformers

* Oral at CVPR 2022, updated version

Access Paper or Ask Questions

A ConvNet for the 2020s

Jan 10, 2022
Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie

Figure 1 for A ConvNet for the 2020s

Figure 2 for A ConvNet for the 2020s

Figure 3 for A ConvNet for the 2020s

Figure 4 for A ConvNet for the 2020s

* Technical report; Code: https://github.com/facebookresearch/ConvNeXt

Access Paper or Ask Questions

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Dec 16, 2021
Chen Wei, Haoqi Fan, Saining Xie, Chao-Yuan Wu, Alan Yuille, Christoph Feichtenhofer

Figure 1 for Masked Feature Prediction for Self-Supervised Visual Pre-Training

Figure 2 for Masked Feature Prediction for Self-Supervised Visual Pre-Training

Figure 3 for Masked Feature Prediction for Self-Supervised Visual Pre-Training

Figure 4 for Masked Feature Prediction for Self-Supervised Visual Pre-Training

* Technical report

Access Paper or Ask Questions

Towards Long-Form Video Understanding

Jun 21, 2021
Chao-Yuan Wu, Philipp Krähenbühl

Figure 1 for Towards Long-Form Video Understanding

Figure 2 for Towards Long-Form Video Understanding

Figure 3 for Towards Long-Form Video Understanding

Figure 4 for Towards Long-Form Video Understanding

* CVPR 2021

Access Paper or Ask Questions

Memory Optimization for Deep Networks

Oct 29, 2020
Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krähenbühl

Figure 1 for Memory Optimization for Deep Networks

Figure 2 for Memory Optimization for Deep Networks

Figure 3 for Memory Optimization for Deep Networks

Figure 4 for Memory Optimization for Deep Networks

* 14 pages, 7 figures; fix minor typos

Access Paper or Ask Questions

Lossless Image Compression through Super-Resolution

Apr 06, 2020
Sheng Cao, Chao-Yuan Wu, Philipp Krähenbühl

Figure 1 for Lossless Image Compression through Super-Resolution

Figure 2 for Lossless Image Compression through Super-Resolution

Figure 3 for Lossless Image Compression through Super-Resolution

Figure 4 for Lossless Image Compression through Super-Resolution

* Tech report

Access Paper or Ask Questions

A Multigrid Method for Efficiently Training Video Models

Dec 02, 2019
Chao-Yuan Wu, Ross Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl

Figure 1 for A Multigrid Method for Efficiently Training Video Models

Figure 2 for A Multigrid Method for Efficiently Training Video Models

Figure 3 for A Multigrid Method for Efficiently Training Video Models

Figure 4 for A Multigrid Method for Efficiently Training Video Models

* Technical report

Access Paper or Ask Questions