A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Do Adversarially Robust ImageNet Models Transfer Better?
[article]
2020
arXiv
pre-print
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
arXiv:2007.08489v2
fatcat:mxupmyuksvhwzjymoo262i4hza