58 citations · 77 across the 7 of their papers we have counts for
5 papers · 1 filter
Causal Transportability for Visual Recognition
Chengzhi Mao, Kevin Xia, James Wang +4
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poo…
Using Multiple Self-Supervised Tasks Improves Model Robustness
Matthew Lawhon, Chengzhi Mao, Junfeng Yang
Deep networks achieve state-of-the-art performance on computer vision tasks, yet they fail under adversarial attacks that are imperceptible to humans. In this paper, we propose a n…
Adversarial Attacks are Reversible with Natural Supervision
Chengzhi Mao, Mia Chiquier, Hao Wang +2
We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterall…
Generative Interventions for Causal Learning
Chengzhi Mao, Augustine Cha, Amogh Gupta +3
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally…
AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
Guangyu Shen, Chengzhi Mao, Junfeng Yang +1
Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models. In this paper, we focus on generating unr…