LibFewShot

Make few-shot learning easy.

Supported Methods

Meta

• MAML(ICML'17)
• ANIL(ICLR'20)
• R2D2(ICLR'19)
• Versa(NeurIPS'18)
• LEO(ICLR'19)
• MTL(CVPR'19)

Metric

• ADM(IJCAI'20)
• ATL-Net(IJCAI'20)
• ProtoNet(NeuraIPS'17)
• RelationNet(CVPR'18)
• ConvaMNet(AAAI'19)
• DN4(CVPR'19)
• CAN(NeuraIPS'19)
• FEAT(CVPR'20)

Finetuning

• Baseline(ICLR'19)
• Baseline++(ICLR'19)
• RFS(ECCV'20)
• SKD(arxiv'20)

Quick Installnation

Please refer to install.md(安装) for installation.

Full tutorials can be found at document(中文文档).

Contributing

Feel free to contribute any kind of function or enhancement, here the coding style follows PEP8. Please refer to contributing.md(贡献代码) for the contributing guideline.

License

This project is licensed under the MIT License. See LICENSE for more details

Acknowledgement

LibFewShot is an open source project designed to help few shot learning researchers quickly understand the classic methods and code structures. We welcome other contributors to use the LibFewShot framework to implement some methods and add them to this library. This library can be used for academic research. We welcome researchers in the field of fes shot learning to use LibFewShot to implement their own methods, and welcome feedback when using LibFewShot. We will try our best to improve the library.

Citation

If you use this code for your research, please cite our paper.

@article{li2021LibFewShot,
  title={LibFewShot: A Comprehensive Library for Few-shot Learning},
  author={Wenbin Li, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Xuesong Yang, Ziyi Wang, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo},
  journal={arXiv preprint arXiv:2109.04898},
  year={2021}
}