MOCA: Masked Online Codebook Assignments prediction

Self-supervised representation learning for Vision Transformers (ViT) to mitigate the greedy needs of ViT networks for very large fully-annotated datasets.

Data and Resources

Cite this as

Spyros Gidaris, Andrei Bursuc, Oriane Simeoni, Antonin Vobecky, Nikos Komodakis, Matthieu Cord, Patrick Pérez (2024). Dataset: MOCA: Masked Online Codebook Assignments prediction. https://doi.org/10.57702/bzs2092i

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Spyros Gidaris
More Authors
Andrei Bursuc
Oriane Simeoni
Antonin Vobecky
Nikos Komodakis
Matthieu Cord
Patrick Pérez
Homepage https://arxiv.org/abs/2206.09544