#self-supervised-learning Repositories
Discover 75 active open source GitHub repositories tagged with #self-supervised-learning, accumulating 155,433 total stars (averaging 2,072 stars per project). Leading this topic is jindongwang/transferlearning with 14,330 stars.
75 repositories total
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials. - Transfer learning
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
A Python library for self-supervised learning and latent world models on images.
An official implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Papers about pretraining and self-supervised learning on Graph Neural Networks (GNNs).
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
Code for TKDE paper "Self-supervised learning on graphs: Contrastive, generative, or predictive"
Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intelยฎ XPU (CUDA also supported).
[ICLR'23 Spotlight๐ฅ] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
A comprehensive list of awesome contrastive self-supervised learning papers.
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning โPropellerโ Bio-Computing Toolkit
Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"
[IEEE T-KDE 2026] Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods (papers, codes, and datasets).
[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.
A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He et al.).
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
[CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling
Frequently Asked Questions
What is the most popular #self-supervised-learning repository on GitHub?
The top ranked open source #self-supervised-learning project on GitHub is jindongwang/transferlearning with 14,330 stars. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials. - Transfer learning
Which programming languages are most used in #self-supervised-learning repositories?
Among the top ranked #self-supervised-learning projects on GitHub, the most common programming languages are Python, Jupyter Notebook, Shell, HTML.
How is the #self-supervised-learning repository ranking calculated?
We track 75 active open source repositories tagged with #self-supervised-learning (500+ stars), totaling 155,433 stars with an average of 2,072 stars per repository. Rankings update daily from the GitHub API.