Methods > General

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
Colorization
2016 78
Jigsaw
2016 53
MoCo
2019 36
SimCLR
2020 33
Contrastive Predictive Coding
2018 32
BYOL
2020 15
MoCo v2
2020 11
BiGAN
2016 10
SwAV
2020 7
NPID
2018 4
BigBiGAN
2019 3
DeepCluster
2018 3
PIRL
2019 3
Contrastive Multiview Coding
2019 2
CPC v2
2019 1
ALP-GMM
2019 1
IMGEP
2017 1
RotNet
2020 1
ClusterFit
2019 1
NPID++
2019 1