https://github.com/clear-nus/selective-amnesia

https://github.com/clear-nus/selective-amnesia

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/clear-nus/selective-amnesia
• Owner: clear-nus
• License: mit
• Created: 2023-05-17T09:58:25.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-09-25T12:28:44.000Z (over 1 year ago)
• Last Synced: 2024-08-01T18:33:37.969Z (6 months ago)
• Language: Python
• Size: 5.48 MB
• Stars: 50
• Watchers: 2
• Forks: 5
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        


# Selective Amnesia: A Continual Learning Approach for Forgetting in Deep Generative Models

[![preprint](https://img.shields.io/static/v1?label=arXiv&message=2301.10120&color=B31B1B)](https://arxiv.org/abs/2305.10120)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

[![Venue:NeurIPS 2023](https://img.shields.io/badge/Venue-NeurIPS%202023-007CFF)](https://nips.cc/)





  

  


  Figure 1: Qualitative results of our method, Selective Amnesia (SA). SA can be applied to a variety

of models, from forgetting textual prompts such as specific celebrities or nudity in text-to-image

models to discrete classes in VAEs and diffusion models (DDPM).



This is the official code repository for the NeurIPS 2023 Spotlight paper [Selective Amnesia: A Continual Learning Approach for Forgetting in Deep Generative Models](https://arxiv.org/abs/2305.10120).

The code is split into three subfolders, one each for VAE, DDPM and Stable Diffusion experiments. Detailed instructions are included in the respective subfolders.

## Contact

If you have any questions regarding the code or the paper, please email [Alvin](mailto:[email protected]).

## BibTeX

If you find this repository or the ideas presented in our paper useful, please consider citing.

```

@article{heng2023selective,

  title={Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models},

  author={Heng, Alvin and Soh, Harold},

  journal={arXiv preprint arXiv:2305.10120},

  year={2023}

}

```