VICReg prevents collapse in self-supervised image embeddings via explicit variance, invariance, and covariance regularization and matches state-of-the-art downstream performance.
Self-supervised learning of pretext-invariant representations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2roles
background 1polarities
background 1representative citing papers
Franca introduces nested Matryoshka clustering and positional disentanglement in a transparent SSL pipeline to deliver open-source vision models competitive with closed proprietary systems.
citing papers explorer
-
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
VICReg prevents collapse in self-supervised image embeddings via explicit variance, invariance, and covariance regularization and matches state-of-the-art downstream performance.
-
Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Franca introduces nested Matryoshka clustering and positional disentanglement in a transparent SSL pipeline to deliver open-source vision models competitive with closed proprietary systems.