Self-Supervised Learning Comparison Hub

4 papers - avg viability 5.0

Reference Surfaces

VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization(7.0)
VINO is a self-supervised learning framework that learns robust image encoders from dense video by imposing a structural information bottleneck, effectively disentangling foreground from background.
Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning(5.0)
Analyze and enhance directional neural collapse for improving few-shot learning in SSL.
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning(4.0)
Bootleg is a self-supervised learning method that enhances feature extraction by predicting latent representations from multiple hidden layers.
IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning(4.0)
IConE offers a novel approach to prevent representation collapse in self-supervised learning, enabling effective training with small batch sizes.