2 papers
cs.LG2021
Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning
Anh Bui, Trung Le, He Zhao +3
Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks. Central to this approach is the selection of posi…
cs.LG2020
Improving Adversarial Robustness by Enforcing Local and Global Compactness
Anh Bui, Trung Le, He Zhao +4
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defens…