Decoupled Contrastive Learning

Contrastive learning is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented views of the same image as positive to be pulled closer, and all other images as negative to be pushed further apart.

Data and Resources

Cite this as

Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen, Yann LeCun (2024). Dataset: Decoupled Contrastive Learning. https://doi.org/10.57702/td83wawx

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Chun-Hsiao Yeh
More Authors
Cheng-Yao Hong
Yen-Chi Hsu
Tyng-Luh Liu
Yubei Chen
Yann LeCun
Homepage https://arxiv.org/abs/2105.04906