solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
-
Updated
Oct 14, 2024 - Python
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
We implement NNCLR and a novel clustering-based technique for contrastive learning that we call KMCLR. We show that applying a clustering technique to obtain prototype embeddings and using these prototypes to form positive pairs for contrastive loss can achieve performances on par with NNCLR on CIFAR-100 while storing 0.4% of the number of vectors.
Add a description, image, and links to the nnclr topic page so that developers can more easily learn about it.
To associate your repository with the nnclr topic, visit your repo's landing page and select "manage topics."