Closed ShellingFord221 closed 2 years ago
Hi, I think they are very different.
The analog to IB in contrastive land would be something like https://arxiv.org/pdf/2109.12909.pdf . The difference with DIB is that DIB :
hope that helps
I suddenly come up with an idea that could DIB motivate augmentation? Since DIB finds representations with sufficiency and minimality, could augmentations based on these representations be more effective and informative? Thanks!
Hi, I just wonder that what is the difference between proposed DIB and conventional contrastive learning? It seems that they both make representations undistinguishable within the class and distinguishable between different classes. Thanks!