Skip to content
/ carp Public

Official PyTorch implementation of Representation Learning via Consistent Assignment of Views over Random Partitions (CARP)

Notifications You must be signed in to change notification settings

sthalles/carp

Repository files navigation

Official implementation of Representation Learning via Consistent Assignment of Views over Random Partitions (CARP)

Thirty-seventh Conference on Neural Information Processing Systems

Important links

Download pre-trained models

Make sure to download CARP's pretraining files and place them in /pretrained/carp/ folder.

Checkpoints can be downloaded here.

Performance

Method Epochs Multicrop Top-1 k-NN URL
CARP 100 2x224 + 6x96 72.5 63.5 CARP-100ep
CARP 200 2x224 + 6x96 74.2 66.5 CARP-100ep
CARP 400 2x224 73.0 67.6 CARP-400ep
CARP 400 2x224 + 6x96 75.3 67.7 CARP-400ep

Running evaluations

To run evaluations, ensure you have a proper Python environment with PyTorch 2.0 and other dependencies.

Go to specific evaluation folders (such as knn or kmeans) for examples of how to run each.

Reference

Please, cite this work as:

@inproceedings{
  Silva2023,
  title={Representation Learning via Consistent Assignment of Views over Random Partitions},
  author={Silva, Thalles and Ram\'irez Rivera, Ad\'in},
  booktitle={Thirty-seventh Conference on Neural Information Processing Systems ({NeurIPS})},
  year={2023},
  url={https://openreview.net/forum?id=fem6BIJkdv}
}

About

Official PyTorch implementation of Representation Learning via Consistent Assignment of Views over Random Partitions (CARP)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published