Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization. (arXiv:2305.00374v1 [cs.LG])

Adversarial contrastive learning (ACL), without requiring labels,
incorporates adversarial data with standard contrastive learning (SCL) and
outputs a robust representation which is generalizable and resistant to
adversarial attacks and common corruptions. The style-independence property of
representations has been validated to be beneficial in improving robustness
transferability. Standard invariant regularization (SIR) has been proposed to
make the learned representations via SCL to be independent of the style
factors. However, how to equip robust representations learned via ACL with the
style-independence property …

acl adversarial adversarial attacks attacks data representation robustness scl standard