Inter-Instance Similarity Modeling for Contrastive Learning

The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential representation degeneration.

Data and Resources

Cite this as

Chengchao Shen, Dawei Liu, Hao Tang, Zhe Qu, Jianxin Wang (2024). Dataset: Inter-Instance Similarity Modeling for Contrastive Learning. https://doi.org/10.57702/3449nq26

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Chengchao Shen
More Authors
Dawei Liu
Hao Tang
Zhe Qu
Jianxin Wang
Homepage https://github.com/visresearch/patchmix