SimCLR learns visual representations by contrasting augmented views of the same image and reaches 76.5% ImageNet top-1 accuracy with a linear classifier, matching a supervised ResNet-50.
K., Gelly, S., and Lucic, M
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
InfoAtlas is a pretrained neural model for zero-shot mutual information estimation that matches state-of-the-art accuracy with 100x speedup and handles varying dimensions via a single model.
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.
M-IDoL learns modality-specific and diverse representations by maximizing inter-modality entropy and minimizing intra-modality uncertainty through information decomposition in MoE subspaces.
citing papers explorer
-
Revisiting Feature Prediction for Learning Visual Representations from Video
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.