Pith. sign in

Self-supervised learning of pretext-invariant representations

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

ACCEPT 1

representative citing papers

A Probabilistic Model for Non-Contrastive Learning

cs.LG · 2025-01-22 · accept · novelty 6.0

A Gaussian generative model of positive pairs has a maximum likelihood estimator that equals PCA under isotropic augmentation noise and equals the simple non-contrastive SSL loss under orthogonal noise.

citing papers explorer

Showing 1 of 1 citing paper.

  • A Probabilistic Model for Non-Contrastive Learning cs.LG · 2025-01-22 · accept · none · ref 3

    A Gaussian generative model of positive pairs has a maximum likelihood estimator that equals PCA under isotropic augmentation noise and equals the simple non-contrastive SSL loss under orthogonal noise.