Do adversarially robust imagenet models transfer better?
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
Do adversarially robust ImageNet models transfer better?
H Salman, A Ilyas, L Engstrom, A Kapoor… - Proceedings of the 34th …, 2020 - dl.acm.org
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 …
datasets can efficiently adapt to downstream tasks. Typically, better pre-trained models yield …
Do Adversarially Robust ImageNet Models Transfer Better?
H Salman, A Ilyas, L Engstrom, A Kapoor… - arXiv e …, 2020 - ui.adsabs.harvard.edu
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
Do Adversarially Robust ImageNet Models Transfer Better?
H Salman, A Ilyas, L Engstrom, A Kapoor… - arXiv preprint arXiv …, 2020 - arxiv.org
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
Do Adversarially Robust ImageNet Models Transfer Better?
H Salman, A Ilyas, L Engstrom… - Advances in Neural …, 2020 - proceedings.neurips.cc
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
[PDF][PDF] Do Adversarially Robust ImageNet Models Transfer Better?
H Salman, A Ilyas, L Engstrom, A Kapoor… - Advances in neural …, 2020 - par.nsf.gov
Transfer learning is a widely-used paradigm in which models pre-trained on standard
datasets can efficiently adapt to downstream tasks. Typically, better pretrained models yield …
datasets can efficiently adapt to downstream tasks. Typically, better pretrained models yield …
[PDF][PDF] Do Adversarially Robust ImageNet Models Transfer Better?
H Salman, A Ilyas, L Engstrom, A Kapoor… - arXiv preprint arXiv …, 2020 - static.aminer.cn
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 …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …