118 citations · 360 across the 17 of their papers we have counts for
4 papers · 1 filter
Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
Haichao Zhang, Jianyu Wang
Conventional adversarial training methods using attacks that manipulate the pixel value directly and individually, leading to models that are less robust in face of spatial transfo…
Towards Adversarially Robust Object Detection
Haichao Zhang, Jianyu Wang
Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance…
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Haichao Zhang, Jianyu Wang
We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches lever…
Improving Sequence-to-Sequence Learning via Optimal Transport
Liqun Chen, Yizhe Zhang, Ruiyi Zhang +7
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word…