Logan Engstrom, Andrew Ilyas, Hadi Salman, Ashish Kapoor
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transfer learning is a widely-used paradigm in which models pre-trained on standard datasets can efficiently adapt 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2007.08489")
get_code_for_paper("2007.08489")
have("2007.08489")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2007.08489.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2007.08489)
Connect an agent — have() is free.