InstDisc |
2018 |
CVPR |
Unsupervised Feature Learning via Non-Parametric Instance Discrimination |
code |
CPC |
2018 |
Arxiv |
Representation Learning with Contrastive Predictive Coding |
code |
DeepCluster |
2018 |
ECCV |
Deep Clustering for Unsupervised Learning of Visual Features |
code |
DIM |
2019 |
ICLR |
Learning deep representations by mutual information estimation and maximization |
code |
InvaSpread |
2019 |
CVPR |
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature |
code |
CMC |
2019 |
CVPR |
Contrastive Multiview Coding |
code |
MoCo_V1 |
2019 |
CVPR |
Momentum Contrast for Unsupervised Visual Representation Learning |
code |
MIMax |
2020 |
ICLR |
On Mutual Information Maximization for Representation Learning |
code |
SimCLR_V1 |
2020 |
ICML |
A Simple Framework for Contrastive Learning of Visual Representations |
code |
MoCo_V2 |
2020 |
CVPR |
Improved Baselines with Momentum Contrastive Learning |
code |
SimCLR_V2 |
2020 |
NeurIPS |
Big Self-Supervised Models are Strong Semi-Supervised Learners |
code |
BYOL |
2020 |
NeurIPS |
Bootstrap Your Own Latent:A New Approach to Self-Supervised Learning |
code |
SWaV |
2020 |
CVPR |
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments |
code |
SimSiam |
2020 |
CVPR |
Exploring Simple Siamese Representation Learning |
code |
MoCo_V3 |
2021 |
ICCV |
An Empirical Study of Training Self-Supervised Vision Transformers |
code |
DetCo |
2021 |
ICCV |
DetCo: Unsupervised Contrastive Learning for Object Detection |
code |
VFT |
2021 |
ICCV |
Improving Contrastive Learning by Visualizing Feature Transformation |
code |
MultiSiam |
2021 |
ICCV |
MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving |
code |
DINO |
2021 |
CVPR |
Emerging Properties in Self-Supervised Vision Transformers |
code |
BarlowTwins |
2021 |
CVPR |
Barlow Twins: Self-Supervised Learning via Redundancy Reduction |
code |
DAPC |
2021 |
ICLR |
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components |
code |
SimMIM |
2021 |
CVPR |
SimMIM: A Simple Framework for Masked Image Modeling |
code |
MAE |
2021 |
2022 CVPR Oral |
Masked Autoencoders Are Scalable Vision Learners |
code |
UniVIP |
2022 |
CVPR |
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training |
None |
ContrastiveCrop |
2022 |
CVPR |
Crafting Better Contrastive Views for Siamese Representation Learning |
code |
HCSC |
2022 |
CVPR |
HCSC: Hierarchical Contrastive Selective Coding |
code |
BEiT |
2022 |
ICLR |
BEiT: BERT Pre-Training of Image Transformers |
code |