A Cookbook of Self-Supervised Learning
It addresses the high barrier to entry in self-supervised learning research for curious researchers, but it is incremental as it compiles existing knowledge rather than introducing new methods.
The paper tackles the complexity of self-supervised learning by providing a foundational guide and recipes to lower the barrier to entry for researchers, aiming to empower them to navigate methods and understand training choices.
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.