Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

Yu-Xiong Wang, Jindong Wang, Haohan Wang, Andy Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• lapisrocks/DiscreteAdversarialDistillation — marked official in Papers with Code

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for better teachers by showing strong gains in out-of-distribution robustness when distilling from pretrained foundation models. Following this finding, we propose Discrete Adversarial Distillation (DAD), which leverages a robust teacher to generate adversarial examples and a VQGAN to discretize them, creating more informative samples than standard data augmentation techniques. We provide a theoretical framework for the use of a robust teacher in the knowledge distillation with data augmentation setting and demonstrate strong gains in out-of-distribution robustness and clean accuracy across different student architectures. Notably, our method adds minor computational overhead compared to similar techniques and can be easily combined with other data augmentations for further improvements.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2311.01441")
get_code_for_paper("2311.01441")
have("2311.01441")

Connect an agent — have() is free.