DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery
By
Yuanpei Liu and
Kai Han.
First, you need to clone the DebGCD repository from GitHub. Open the terminal and run the following command:
git clone https://github.com/Visual-AI/DebGCD.git
cd DebGCD
We recommend setting up a conda environment for the project:
conda create --name=debgcd python=3.8
conda activate debgcd
pip install -r requirements.txtSet paths to datasets, pretrained weights, and log directories in config.py
We use generic object recognition datasets, including CIFAR-10/100 and ImageNet-100:
We also use fine-grained benchmarks (CUB, Stanford-cars, FGVC-aircraft). You can find the datasets in:
We use the slurm system to run the code. The scripts to train and eval DebGCD models on different datasets can be found in the folder /scripts. For example, to train and eval on Stanford Cars dataset.
Eval the model
sbatch scripts/eval_DebGCD.cmd scars
Train the model:
sbatch scripts/train_scars.cmd
Please note that we have further tuned the hyperparameters to get optimal performance on each dataset, which can be slightly different under different conda environments. So, it's suggested to use install the environment following the provided requirements. Our models can be downloaded from this link.
If you find this repo useful for your research, please consider citing our paper:
@inproceedings{liu2025debgcd,
title={DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery},
author={Liu, Yuanpei and Han, Kai},
booktitle={ICLR},
year={2025}
}