The strategy, which is named REMEDIS (for ‘Robust and Efficient Medical Imaging with Self-supervision’), combines large-scale supervised transfer learning on natural images and intermediate contrastive self-supervised learning on medical images and requires minimal task-specific customization.
Basil Mustafa
6 papers
Sebastien Baur
1 papers
Simon Kornblith
2 papers
Ting Chen
1 papers
Nenad Tomašev
3 papers
Jovana Mitrovic
1 papers
Patricia Strachan
2 papers
S. S. Mahdavi
3 papers
Ellery Wulczyn
2 papers
Boris Babenko
3 papers
Megan Walker
1 papers
Aaron Loh
1 papers
Po-Hsuan Cameron Chen
1 papers
Yuan Liu
2 papers
Pinal Bavishi
1 papers
S. McKinney
2 papers
Jim Winkens
2 papers
Abhijit Guha Roy
5 papers
Zach Beaver
1 papers
Fiona Ryan
3 papers
Justin D. Krogue
1 papers
M. Etemadi
1 papers
Umesh Telang
1 papers
Yun Liu
6 papers
L. Peng
6 papers
G. Corrado
6 papers
D. Webster
4 papers
David J. Fleet
7 papers
Geoffrey E. Hinton
13 papers
N. Houlsby
12 papers
A. Karthikesalingam
2 papers
Mohammad Norouzi
14 papers
Vivek Natarajan
5 papers