/class-incremental-learning

PyTorch implementation for AANets (CVPR 2021) and Mnemonics Training (CVPR 2020)

Primary LanguagePythonMIT LicenseMIT

Class-Incremental Learning

LICENSE Python

News

  • We update the code for Adaptive Aggregation Networks (accepted to CVPR 2021), which achieve SOTA performance on class-incremental learning tasks. Detailed comments are added for most of the functions and classes.

Papers

  • Adaptive Aggregation Networks for Class-Incremental Learning, CVPR 2021. [PDF] [Project]

  • Mnemonics Training: Multi-Class Incremental Learning without Forgetting, CVPR 2020. [PDF] [Project]

Citations

Please cite our paper if it is helpful to your work:

@inproceedings{Liu2020AANets,
  author    = {Liu, Yaoyao an Schiele, Bernt and Sun, Qianru},
  title     = {Adaptive Aggregation Networks for Class-Incremental Learning},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2021}
}
@inproceedings{liu2020mnemonics,
author    = {Liu, Yaoyao and Su, Yuting and Liu, An{-}An and Schiele, Bernt and Sun, Qianru},
title     = {Mnemonics Training: Multi-Class Incremental Learning without Forgetting},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages     = {12245--12254},
year      = {2020}
}

Acknowledgements

Our implementation uses the source code from the following repositories: