awesome-self-supervised-learning and awesome-semi-supervised-learning

These tools are complements because self-supervised learning can be used to generate labeled data for semi-supervised learning, with both being approaches to leverage unlabeled data effectively.

Maintenance 10/25
Adoption 10/25
Maturity 8/25
Community 22/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 6,370
Forks: 837
Downloads:
Commits (30d): 0
Language:
License:
Stars: 1,853
Forks: 230
Downloads:
Commits (30d): 0
Language:
License: MIT
No License No Package No Dependents
Stale 6m No Package No Dependents

About awesome-self-supervised-learning

jason718/awesome-self-supervised-learning

A curated list of awesome self-supervised methods

Comprehensively catalogs self-supervised learning papers across domains—computer vision, NLP, robotics, graph networks, and time-series—with links to PDFs and implementations. Organizes methods by approach (contrastive learning, generative models, pretext tasks) and includes theoretical foundations, benchmark codebases, and video/3D representation techniques. Covers both foundational architectures and recent developments, serving as a resource aggregator for researchers implementing SSL across PyTorch/TensorFlow ecosystems.

About awesome-semi-supervised-learning

yassouali/awesome-semi-supervised-learning

😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

Organizes papers across domain-specific categories (computer vision, NLP, generative models, graph-based methods, theory) with direct links to PDFs and implementations, enabling researchers to navigate SSL literature by application area and methodology. Includes foundational resources like survey papers, textbooks, and recorded talks alongside contemporary deep learning adaptations of classical SSL techniques such as consistency regularization and pseudo-labeling. Actively maintained with community contributions following a standardized markdown format for adding new papers and codebases.

Scores updated daily from GitHub, PyPI, and npm data. How scores work