Skip to content
#

nnclr

Star

Here are 2 public repositories matching this topic...

mwritescode / nnclr-cifar100

Star 2

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.

clustering k-means cifar-100 self-supervised-learning contrastive-learning nnclr
  • Updated Feb 8, 2023
  • Python

Add this topic to your repo

To associate your repository with the nnclr topic, visit your repo's landing page and select "manage topics."

Learn more