IMSVD softly discretizes latent variables and uses a cross-joint entropy loss to learn transform-invariant, non-collapsed, redundancy-minimized image representations without labels.
A simple framework for contrastive learning of visual representations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning
IMSVD softly discretizes latent variables and uses a cross-joint entropy loss to learn transform-invariant, non-collapsed, redundancy-minimized image representations without labels.