Fast Bi-level Adversarial Training

Introduced by Zhang et al. in Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Fast-BAT is a new method for accelerated adversarial training.

Source: Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Read Paper See Code

Paper	Code	Results	Date	Stars

Task	Papers	Share
Adversarial Defense	1	100.00%

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign