Self-Supervised Learning

Self-Supervised Learning refers to a category of methods where we learn representations in a self-supervised way (i.e without labels). These methods generally involve a pretext task that is solved to learn a good representation and a loss function to learn with. Below you can find a continuously updating list of self-supervised methods.

METHOD YEAR PAPERS
Contrastive Predictive Coding
2018 20
BiGAN
2016 9
MoCo
2019 6
SimCLR
2020 3
BigBiGAN
2019 3
MoCo v2
2020 2
CPC v2
2019 1
Contrastive Multiview Coding
2019 1
SwAV
2020 1