Skip to content
#

cifar-100

Here are 61 public repositories matching this topic...

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.

  • Updated Feb 8, 2023
  • Python

Improve this page

Add a description, image, and links to the cifar-100 topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cifar-100 topic, visit your repo's landing page and select "manage topics."

Learn more