EquiMod: An Equivariance Module to Improve Visual Instance Discrimination

Recent self-supervised visual representation methods are closing the gap with supervised learning performance. Most of these successful methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations.

Data and Resources

Cite this as

Alexandre Devillers, Mathieu Lefort (2024). Dataset: EquiMod: An Equivariance Module to Improve Visual Instance Discrimination. https://doi.org/10.57702/uk06s9hq

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Alexandre Devillers
More Authors
Mathieu Lefort
Homepage https://github.com/ADevillers/