Antonin Vobecky
@vobeckya.bsky.social
Ph.D. at CTU in Prague, multi-modal computer vision
supervised by Josef Sivic and Patrick Pérez
https://vobecant.github.io/
supervised by Josef Sivic and Patrick Pérez
https://vobecant.github.io/
Reposted by Antonin Vobecky
MOCA ☕: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
by S. Gidaris, A. Bursuc, O. Simeoni, A. Vobecky, N. Komodakis, M. Cord, P. Pérez
Unify mask-and-predict & contrastive SSL objectives -> better performance w/ 3x faster training
by S. Gidaris, A. Bursuc, O. Simeoni, A. Vobecky, N. Komodakis, M. Cord, P. Pérez
Unify mask-and-predict & contrastive SSL objectives -> better performance w/ 3x faster training
April 9, 2025 at 9:38 AM
MOCA ☕: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
by S. Gidaris, A. Bursuc, O. Simeoni, A. Vobecky, N. Komodakis, M. Cord, P. Pérez
Unify mask-and-predict & contrastive SSL objectives -> better performance w/ 3x faster training
by S. Gidaris, A. Bursuc, O. Simeoni, A. Vobecky, N. Komodakis, M. Cord, P. Pérez
Unify mask-and-predict & contrastive SSL objectives -> better performance w/ 3x faster training