Do Adversarially Robust ImageNet Models Transfer Better?

  • Hadi Salman ,
  • Andrew Ilyas ,
  • Logan Engstrom ,
  • Ashish Kapoor ,
  • Aleksander Madry

ArXiv

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that initial accuracy is a key aspect of transfer learning performance. In this work, we identify another such aspect: we find that adversarially robust models, while less accurate, often perform better than their standard-trained counterparts when used for transfer learning. Specifically, we focus on adversarially robust ImageNet classifiers, and show that they yield improved accuracy on a standard suite of downstream classification tasks. Further analysis uncovers more differences between robust and standard models in the context of transfer learning. Our results are consistent with (and in fact, add to) recent hypotheses stating that robustness leads to improved feature representations. Our code and models are available at https://github.com/microsoft/robust-models-transfer (opens in new tab).

论文与出版物下载

Transfer Learning using Adversarially Robust ImageNet models

21 7 月, 2020

This repository contains the code and models necessary to replicate the results of our paper: Do Adversarially Robust ImageNet Models Transfer Better? Hadi Salman*, Andrew Ilyas*, Logan Engstrom, Ashish Kapoor, Aleksander Madry