“A Cookbook of Self-Supervised Learning”, Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Gregoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum2023-04-24 (data-augmented GANs, knowledge distillation, CLIP, masked autoencoder)⁠:

Self-supervised learning, dubbed the ‘dark matter of intelligence’, is a promising path to advance machine learning.

Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook.

We hope to empower the curious researcher to navigate the terrain of methods, understand the role of the various knobs, and gain the know-how required to explore how delicious SSL can be.

[The Deep Metric Learning Family: SimCLR/NNCLR/MeanSHIFT/SLC; The Self-Distillation Family: BYOL/SimSIAM/DINO; The Canonical Correlation Analysis Family: VICReg/BarlowTwins/SWAV/W-MSE; Masked Image Modeling (MIM): BEiT/MAE/SimMIM/Muse.]