activity
20202022
most citedChaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

17 citations · 44 across the 11 of their papers we have counts for

collaborators

13 papers

cs.CV202214 cited

When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture

Yichuan Mo, Dongxian Wu, Yifei Wang +2

Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provid…

cs.LG20225 cited

Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors

Qixun Wang, Yifei Wang, Hong Zhu +1

Deep models often fail to generalize well in test domains when the data distribution differs from that in the training domain. Among numerous approaches to address this Out-of-Dist…

cs.LG20221 cited

Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization

Yifei Wang, Peng Chen, Mert Pilanci +1

The computation of Wasserstein gradient direction is essential for posterior sampling problems and scientific computing. The approximation of the Wasserstein gradient with finite s…

cs.LG20221 cited

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training

Yifei Wang, Yisen Wang, Jiansheng Yang +1

Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good gene…

cs.LG202217 cited

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

Yifei Wang, Qi Zhang, Yisen Wang +2

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. I…

cs.LG20213 cited

Residual Relaxation for Multi-view Representation Learning

Yifei Wang, Zhengyang Geng, Feng Jiang +4

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we no…