https://github.com/ShipengWang/Adam-NSCL

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"
https://github.com/ShipengWang/Adam-NSCL

continual-learning incremental-learning lifelong-learning

Last synced: about 2 months ago
JSON representation

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

• Host: GitHub
• URL: https://github.com/ShipengWang/Adam-NSCL
• Owner: ShipengWang
• License: mit
• Created: 2021-03-04T10:39:05.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2021-07-24T12:45:28.000Z (over 3 years ago)
• Last Synced: 2024-08-04T03:11:08.702Z (5 months ago)
• Topics: continual-learning, incremental-learning, lifelong-learning
• Language: Python
• Homepage:
• Size: 3.74 MB
• Stars: 46
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Adam-NSCL

This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper:

**Title**: [Training Networks in Null Space of Feature Covariance for Continual Learning](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Training_Networks_in_Null_Space_of_Feature_Covariance_for_Continual_CVPR_2021_paper.pdf)

**Authors**: Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

**Email**: [email protected]; [email protected]

**Arxiv**: https://arxiv.org/pdf/2103.07113

Usage

-

```

sh scripts_svd/adamnscl.sh

```

**Requirements**: Python 3.7, PyTorch=1.5,tensorboardX

Citation

```

@InProceedings{Wang_2021_CVPR,

    author    = {Wang, Shipeng and Li, Xiaorong and Sun, Jian and Xu, Zongben},

    title     = {Training Networks in Null Space of Feature Covariance for Continual Learning},

    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

    month     = {June},

    year      = {2021},

    pages     = {184-193}

}

```