Add new SOTA Contrastive Learning methods
sccbhxc opened this issue · comments
We appreciate your effort on the maintenance of this awesome repository.
We would like to recommend our recent research works on contrastive learning, which achieve state-of-the-art performance on popular benchmarks.
The papers are listed as follows:
Inter-Instance Similarity Modeling for Contrastive Learning
Asymmetric Patch Sampling for Contrastive Learning
Both of them provides open source code and trained model weights at Github, which can be found at following links:
https://github.com/visresearch/patchmix
https://github.com/visresearch/aps
Thanks!
merged you pr.