OpenMMLab website ^HOT      OpenMMLab platform ^{TRY IT OUT}

 

📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🤔Reporting Issues

English | 简体中文

Introduction

MMSelfSup is an open source self-supervised representation learning toolbox based on PyTorch. It is a part of the OpenMMLab project.

The master branch works with PyTorch 1.5 or higher.

Major features

• Methods All in One

  MMSelfsup provides state-of-the-art methods in self-supervised learning. For comprehensive comparison in all benchmarks, most of the pre-training methods are under the same setting.

• Modular Design

  MMSelfSup follows a similar code architecture of OpenMMLab projects with modular design, which is flexible and convenient for users to build their own algorithms.

• Standardized Benchmarks

  MMSelfSup standardizes the benchmarks including logistic regression, SVM / Low-shot SVM from linearly probed features, semi-supervised classification, object detection and semantic segmentation.

• Compatibility

  Since MMSelfSup adopts similar design of modulars and interfaces as those in other OpenMMLab projects, it supports smooth evaluation on downstream tasks with other OpenMMLab projects like object detection and segmentation.

What's New

Preview of 1.x version

A brand new version of MMSelfSup v1.0.0rc1 was released in 01/09/2022:

Highlights of the new version:

• Based on MMEngine and MMCV.
• Released with refactor.
• Refine all documents.
• Support MAE, SimMIM, MoCoV3 with different pre-training epochs and backbones of different scales.
• More concise API.
• More powerful data pipeline.
• Higher accurcy for some algorithms.

Find more new features in 1.x branch. Issues and PRs are welcome!

Stable version

MMSelfSup v0.10.0 was released in 30/09/2022.

Highlights of the new version:

• Support MaskFeat

Please refer to changelog.md for details and release history.

Differences between MMSelfSup and OpenSelfSup codebases can be found in compatibility.md.

Installation

MMSelfSup relies on PyTorch, MMCV and MMClassification.

Please refer to install.md for more detailed instruction.

Get Started

Please refer to prepare_data.md for dataset preparation, get_started.md for the basic usage and benchmarks.md for running benchmarks.

We also provides more detailed tutorials:

• config
• add new dataset
• data pipeline
• add new module
• customize schedules
• customize runtime

Besides, we provide colab tutorial for basic usage.

Please refer to FAQ for frequently asked questions.

Model Zoo

Please refer to model_zoo.md for a comprehensive set of pre-trained models and benchmarks.

Supported algorithms:

• Relative Location (ICCV'2015)
• Rotation Prediction (ICLR'2018)
• DeepCluster (ECCV'2018)
• NPID (CVPR'2018)
• ODC (CVPR'2020)
• MoCo v1 (CVPR'2020)
• SimCLR (ICML'2020)
• MoCo v2 (ArXiv'2020)
• BYOL (NeurIPS'2020)
• SwAV (NeurIPS'2020)
• DenseCL (CVPR'2021)
• SimSiam (CVPR'2021)
• Barlow Twins (ICML'2021)
• MoCo v3 (ICCV'2021)
• MAE (CVPR'2022)
• SimMIM (CVPR'2022)
• MaskFeat (CVPR'2022)
• CAE (ArXiv'2022)

More algorithms are in our plan.

Benchmark

Benchmarks	Setting
ImageNet Linear Classification (Multi-head)	Goyal2019
ImageNet Linear Classification (Last)
ImageNet Semi-Sup Classification
Places205 Linear Classification (Multi-head)	Goyal2019
iNaturalist2018 Linear Classification (Multi-head)	Goyal2019
PASCAL VOC07 SVM	Goyal2019
PASCAL VOC07 Low-shot SVM	Goyal2019
PASCAL VOC07+12 Object Detection	MoCo
COCO17 Object Detection	MoCo
Cityscapes Segmentation	MMSeg
PASCAL VOC12 Aug Segmentation	MMSeg

Contributing

We appreciate all contributions improving MMSelfSup. Please refer to CONTRIBUTING.md for more details about the contributing guideline.

Acknowledgement

MMSelfSup is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new algorithms.

MMSelfSup originates from OpenSelfSup, and we appreciate all early contributions made to OpenSelfSup. A few contributors are listed here: Xiaohang Zhan (@XiaohangZhan), Jiahao Xie (@Jiahao000), Enze Xie (@xieenze), Xiangxiang Chu (@cxxgtxy), Zijian He (@scnuhealthy).

Citation

If you use this toolbox or benchmark in your research, please cite this project.

@misc{mmselfsup2021,
    title={{MMSelfSup}: OpenMMLab Self-Supervised Learning Toolbox and Benchmark},
    author={MMSelfSup Contributors},
    howpublished={\url{https://github.com/open-mmlab/mmselfsup}},
    year={2021}
}

License

This project is released under the Apache 2.0 license.

Projects in OpenMMLab

• MMCV: OpenMMLab foundational library for computer vision.
• MIM: MIM installs OpenMMLab packages.
• MMClassification: OpenMMLab image classification toolbox and benchmark.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
• MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
• MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
• MMRazor: OpenMMLab model compression toolbox and benchmark.
• MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
• MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMFlow: OpenMMLab optical flow toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.
• MMGeneration: OpenMMLab image and video generative models toolbox.
• MMDeploy: OpenMMLab model deployment framework.