Self-supervised learning
Self-supervised learning deals with learning from unlabeled sample data. It can be regarded as an intermediate form between AI/Supervised Learning/Supervised learning and AI/Unsupervised learning/Unsupervised learning
See “Self-supervised vision transformers” subsection in AI/Deep learning/Transformers
# Resources
- https://github.com/jason718/awesome-self-supervised-learning
- https://en.wikipedia.org/wiki/Self-supervised_learning
- https://hackernoon.com/self-supervised-learning-gets-us-closer-to-autonomous-learning-be77e6c86b5a
- Self-Supervised Representation Learning
- Self-Supervised Vision Models (2021, Dr. Ishan Misra - FAIR)
- Self-supervised learning: The dark matter of intelligence
- The general technique of self-supervised learning is to predict any unobserved or hidden part (or property) of the input from any observed or unhidden part of the input
- Blog post explained
- Grokking self-supervised (representation) learning: how it works in computer vision and why
- Self-supervised learning tutorial: Implementing SimCLR with pytorch lightning
# Code
- #CODE
VISSL
- FAIR’s library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images
- #CODE
Solo-learn
- A library of self-supervised methods for unsupervised visual representation learning powered by PyTorch Lightning
- Methods available: Barlow Twins, BYOL, DeepCluster V2, DINO, MoCo V2+, NNCLR, ReSSL, SimCLR + Supervised Contrastive Learning, SimSiam, Swav, VICReg, W-MSE
- https://arxiv.org/abs/2108.01775v2
- #CODE
Lightly
- A python library for self-supervised learning on images
- #CODE
OpenSelfSup
- Self-Supervised Learning Toolbox and Benchmark
- #CODE
Curator
- A No-Code, Self-Supervised Learning and Active Labeling Tool to Create Labeled Image Datasets from Petabyte-Scale Imagery
# References
- #PAPER Self-Supervised Learning of Pretext-Invariant Representations (Misra 2019)
- #PAPER A Framework For Contrastive Self-Supervised Learning And Designing A New Approach (Falcon 2020)
- #PAPER RegNet - Designing Network Design Spaces (Radosavovic 2020)
- #PAPER Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning (Haghighi 2021)
- #PAPER Instance Localization for Self-supervised Detection Pretraining (Yang 2021)
- #PAPER
Supervised Contrastive Learning (Khosla 2021)
- #CODE https://github.com/google-research/google-research/tree/master/supcon
- #CODE https://keras.io/examples/vision/supervised-contrastive-learning/
- extended the self-supervised batch contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information
- clusters of points belonging to the same class are pulled together in embedding space, while simultaneously pushing apart clusters of samples from different classes
- #PAPER Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language (Auli 2022)