https://github.com/linhaowei1/CLoG

✌ CLoG: Benchmarking Continual Learning of Image Generation Models
https://github.com/linhaowei1/CLoG

continual-learning diffusion-models gan generative-model huggingface machine-learning stable-diffusion

Last synced: 13 days ago
JSON representation

✌ CLoG: Benchmarking Continual Learning of Image Generation Models

• Host: GitHub
• URL: https://github.com/linhaowei1/CLoG
• Owner: linhaowei1
• License: mit
• Created: 2024-06-06T15:19:45.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-06-10T02:46:39.000Z (5 months ago)
• Last Synced: 2024-08-01T18:33:35.969Z (3 months ago)
• Topics: continual-learning, diffusion-models, gan, generative-model, huggingface, machine-learning, stable-diffusion
• Language: Python
• Homepage:
• Size: 4.05 MB
• Stars: 13
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        


  

    

  





 | [日本語](docs/README_JP.md) | [English](https://github.com/linhaowei1/CLoG) | [中文简体](docs/README_CN.md) | [中文繁體](docs/README_TW.md) |



---



Code and data for our paper CLoG: Benchmarking Continual Learning of Image Generation Models

    

    

    

        

    

    

        

    

    

        

    



## 📰 News

* **[Jun. 7, 2024]**: We launch the first version of code for *label-conditioned CLoG*. Our codebase is still in development, please stay tuned for the comprehensive version.

## 👋 Overview

We advocates for shifting the research focus from classification-based continual learning (CL) to **continual learning of generative models (CLoG)**. Our codebase adapts 12 existing CL methodologies of three types—replay-based, regularization-based, and parameter-isolation-based methods—to generative tasks and introduce 8 benchmarks for CLoG that feature great diversity and broad task coverage. 





## 🚀 Set Up

To run CLoG from source, follow these steps:

1. Clone this repository locally

2. `cd` into the repository.

3. Run `conda env create -f environment.yml` to created a conda environment named `CLoG`.

4. Activate the environment with `conda activate CLoG`.

## 💽 Usage

Coming soon! For the time being, you can check `scripts/cifar-naive.sh` for running NCL on CIFAR-10.

## 💫 Contributions

We would love to hear from the CL community, broader machine learning, and generative AI communities, and we welcome any contributions, pull requests, or issues!

To do so, please either file a new pull request or issue. We'll be sure to follow up shortly!

## ✍️ Citation

If you find our work helpful, please use the following citations.

```

@article{

    zhang2024clog,

    title={CLoG: Benchmarking Continual Learning of Image Generation Models},

    author={Haotian Zhang and Junting Zhou and Haowei Lin and Hang Ye and Jianhua Zhu and Zihao Wang and Liangcai Gao and Yizhou Wang and Yitao Liang},

    booktitle={arxiv},

    year={2024}

}

```

## 🪪 License

MIT. Check `LICENSE.md`.