Tweeted By @ak92501
SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
— AK (@ak92501) June 30, 2021
pdf: https://t.co/YmfyNkLcC9
abs: https://t.co/m4kiQq0j5Q
technique for contrastive learning, where views are formed by corrupting a random subset of features pic.twitter.com/pP6phV9p3m