This repo is the implementation of HiBug: On Human-Interpretable Model Debug. HiBug is a data centric tool for investigating bugs in visual deep learning, such as rare cases in dataset, model's correlation on visual feature.
- Utilizes large language models and vision-language models for bug discovery and repair.
- Provides a human-understandable debugging process.
- Equipped with a user interface.
- Clone the repository.
- Set up the environment.
conda create -n HiBug python=3.7
conda activate HiBug
pip install -r requirements.txt
- Get a ChatGPT API key. (Optional)
- Follow the steps in run.ipynb.
We provide a use case on celebA dataset in Code
If you find this repository useful for your work, please consider citing it as follows:
@inproceedings{chen2023hibug,
title={HiBug: On Human-Interpretable Model Debug},
author={Chen, Muxi and Li, Yu and Xu, Qiang},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023}
}