Below is the relations among Unsupervised Learning, Self-Supervised Learning and Representation Learning. This repo focuses on the shadow area, i.e., Unsupervised Representation Learning. Self-Supervised Representation Learning is the major branch of it. Since in many cases we do not distingush between Self-Supervised Representation Learning and Unsupervised Representation Learning strictly, we still name this repo as `OpenSelfSup`.
<em>For comprehensive comparison in all benchmarks, refer to [MODEL_ZOO.md](docs/MODEL_ZOO.md). Most of the selfsup pretraining methods are under the `batch_size=256, epochs=200` setting.</em>
`OpenSelfSup` follows a similar code architecture of MMDetection while is even more flexible than MMDetection, since OpenSelfSup integrates various self-supervised tasks including classification, joint clustering and feature learning, contrastive learning, tasks with a memory bank, etc.
For existing methods in this repo, you only need to modify config files to adjust hyper-parameters. It is also simple to design your own methods, please refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md).
All methods support multi-machine multi-gpu distributed training.
- **Standardized Benchmarks**
We standardize the benchmarks including logistic regression, SVM / Low-shot SVM from linearly probed features, semi-supervised classification, and object detection. Below are the setting of these benchmarks.
| ImageNet Linear Classification (Multi) | [goyal2019scaling](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) | Evaluate different layers. |
| ImageNet Linear Classification (Last) | [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) | Evaluate the last layer after global pooling. |
| Places205 Linear Classification | [goyal2019scaling](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) | Evaluate different layers. |
| ImageNet Semi-Sup Classification |
| PASCAL VOC07 SVM | [goyal2019scaling](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) | Costs="1.0,10.0,100.0" to save evaluation time w/o change of results. |
| PASCAL VOC07 Low-shot SVM | [goyal2019scaling](http://openaccess.thecvf.com/content_ICCV_2019/papers/Goyal_Scaling_and_Benchmarking_Self-Supervised_Visual_Representation_Learning_ICCV_2019_paper.pdf) | Costs="1.0,10.0,100.0" to save evaluation time w/o change of results. |
We encourage researchers interested in Self-Supervised Learning to contribute to OpenSelfSup. Your contributions, including implementing or transferring new methods to OpenSelfSup, performing experiments, reproducing of results, parameter studies, etc, will be recorded in [MODEL_ZOO.md](docs/MODEL_ZOO.md). For now, the contributors include: Xiaohang Zhan ([@XiaohangZhan](http://github.com/XiaohangZhan)), Jiahao Xie ([@Jiahao000](https://github.com/Jiahao000)), Enze Xie ([@xieenze](https://github.com/xieenze)), Xiangxiang Chu ([@cxxgtxy](https://github.com/cxxgtxy)), Zijian He ([@scnuhealthy](https://github.com/scnuhealthy)).
This repo is currently maintained by Xiaohang Zhan ([@XiaohangZhan](http://github.com/XiaohangZhan)), Jiahao Xie ([@Jiahao000](https://github.com/Jiahao000)) and Enze Xie ([@xieenze](https://github.com/xieenze)).
