This repository is a curated list of resources for self-supervised learning (SSL), targeting researchers and engineers in AI. It provides a comprehensive overview of papers, code, and benchmarks across various domains like computer vision, NLP, and robotics, aiming to consolidate knowledge and facilitate contributions to the field.

How It Works

The list is organized by sub-fields within self-supervised learning, categorizing papers by their approach (e.g., contrastive, generative, predictive) and application area. Each entry typically includes the paper title, PDF link, code repository link, authors, and publication venue/year, allowing users to easily find and access relevant research.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required. The primary "requirement" is an interest in self-supervised learning research.

Highlighted Details

• Extensive categorization covering Theory, Computer Vision, NLP, Audio, Robotics, Time-Series, and Graphs.
• Includes links to key benchmarks like FAIR Self-Supervision Benchmark and papers evaluating transfer learning capabilities.
• Features seminal works and recent advancements, with a clear chronological progression for many sub-fields.
• Provides links to talks, theses, and blog posts for broader understanding and community engagement.

Maintenance & Community

The list is maintained by Zhongzheng Ren and is open for community contributions via pull requests. It is inspired by other "awesome" lists in the AI community.

Licensing & Compatibility

The content is available under a public domain dedication (CC0), allowing for unrestricted use and modification.

Limitations & Caveats

As a curated list, its comprehensiveness is dependent on community contributions and the curator's selection. It does not provide a unified framework or implementation but rather a directory of research.