Adversarial Self-Supervised Contrastive Learning

The authors propose a novel instance-wise adversarial perturbation method and a self-supervised contrastive learning framework to train an adversarially robust neural network without any class labels.

Data and Resources

Cite this as

Minseon Kim, Jihoon Tack, Sung Ju Hwang (2025). Dataset: Adversarial Self-Supervised Contrastive Learning. https://doi.org/10.57702/4v10hpb2

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2006.07589
Author Minseon Kim
More Authors
Jihoon Tack
Sung Ju Hwang
Homepage https://github.com/Kim-Minseon/RoCL