Tweeted By @quantombone
What Should Not Be Contrastive in Contrastive Learning.
— Tomasz Malisiewicz (@quantombone) August 14, 2020
The model learns to capture varying and invariant factors for visual representations by constructing separate embedding spaces, each of which is invariant to all but one augmentation.https://t.co/YKQUzLN6TH#computervision pic.twitter.com/l7SzTkCvMG