charlesCXK / PixelSSL

A PyTorch-based Semi-Supervised Learning (SSL) Codebase for Pixel-wise (Pixel) Vision Tasks

---

PixelSSL is a PyTorch-based semi-supervised learning (SSL) codebase for pixel-wise (Pixel) vision tasks.

The purpose of this project is to promote the research and application of semi-supervised learning on pixel-wise vision tasks. PixelSSL provides two major features:

• Interface for implementing new semi-supervised algorithms
• Template for encapsulating diverse computer vision tasks

As a result, the SSL algorithms integrated in PixelSSL are compatible with all task codes inherited from the given template.

This project includes the code of our ECCV 2020 paper Guided Collaborative Training for Pixel-wise Semi-Supervised Learning (GCT).

News:

• [Aug 13 2019] PixelSSL v0.1.0 is Published!
  v0.1.0 supports supervised-only learning, three semi-supervised learning algorithms (MT, AdvSSL, GCT) and one example task (semantic segmentation).

  [More]

Supported Algorithms and Tasks

We are actively updating this project.
The algorithms and demo tasks supported by PixelSSL are summarized in the following table:

SSL/Tasks	Segmentation	Other Tasks
SupOnly	v0.1.0	Coming Soon
MT	v0.1.0	Coming Soon
S4L	Coming Soon	Coming Soon
AdvSSL	v0.1.0	Coming Soon
GCT	v0.1.0	Coming Soon

Installation

Please refer to the Installation document.

Getting Started

Please follow the Getting Started document to run the provided demo tasks.

Tutorials

We provide the API document and some tutorials for using PixelSSL.

• Tutorial 1 - Implement A New Pixel-wise Semi-Supervised Algorithm
• Tutorial 2 - Implement A New Pixel-wise Task Based on the Task Template
• Tutorial 3 - Dataset Wrappers for Semi-Supervised Learning
• Tutorial 4 - Support More Optimizers and LRSchedulers

License

This project is released under the Apache 2.0 license.

Acknowledgement

We thank City University of Hong Kong and SenseTime for their support to this project.

Citation

This project is extended from our ECCV 2020 paper Guided Collaborative Training for Pixel-wise Semi-Supervised Learning (GCT). If this codebase or our method helps your research, please cite:

@InProceedings{ke2020gct,
  author = {Ke, Zhanghan and Qiu, Di and Li, Kaican and Yan, Qiong and Lau, Rynson W.H.},
  title = {Guided Collaborative Training for Pixel-wise Semi-Supervised Learning},
  booktitle = {European Conference on Computer Vision (ECCV)},
  month = {August},
  year = {2020},
}

Contact

This project is currently maintained by Zhanghan Ke (@ZHKKKe).
If you have any questions, please feel free to contact [e-mail].