PaperICML 2020 · 2020
A Simple Framework for Contrastive Learning of Visual Representations
1page built on it
2more pages cite it
1narrative
2registry papers cite it
In the Atlas
ConceptPrimary source of
Self-Supervised Learning
Survey of label-free visual representation learning: contrastive objectives (SimCLR, MoCo) and negative-free self-distillation (BYOL, DINO), with a decision table and the collapse mechanics that separate them.
Appears in 1 narrative
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 2
Builds on · 5
2012ImageNet Classification with Deep Convolutional Neural NetworksKrizhevsky, Sutskever, Hinton2014Very Deep Convolutional Networks for Large-Scale Image RecognitionSimonyan, Zisserman2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftIoffe, Szegedy2015Going deeper with convolutionsSzegedy, Liu et al.2016Deep Residual Learning for Image RecognitionHe, Zhang et al.