DebGCD

KO | EN

gitlite — search

#react #ai #typescript #llm #golang #go #docker #macos #windows #cli #awesome-list #pytorch #security #mcp

(★ 16)

[ICLR 2025] DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery

DebGCD Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

#  DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery (ICLR 2025)

<a href="https://arxiv.org/abs/2504.04804"><img src="https://img.shields.io/badge/arXiv-2504.06120-b31b1b"></a>
 <a href="https://visual-ai.github.io/debgcd/"><img src="https://img.shields.io/badge/Project-Website-blue"></a>
 <a href="#jump"><img src="https://img.shields.io/badge/Citation-8A2BE2"></a>


	DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery 
 By
 Yuanpei Liu and 
 Kai Han.

## Prerequisite 🛠️

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:

```bash
conda create --name=debgcd python=3.8
conda activate debgcd
pip install -r requirements.txt
```

## Running 🏃
### Config

Set paths to datasets, pretrained weights, and log directories in ``config.py``

### Datasets

We use generic object recognition datasets, including CIFAR-10/100 and ImageNet-100:

* [CIFAR-10/100](https://pytorch.org/vision/stable/datasets.html) and [ImageNet-100](https://image-net.org/download.php)

We also use fine-grained benchmarks (CUB, Stanford-cars, FGVC-aircraft). You can find the datasets in:

* [The Semantic Shift Benchmark (SSB)](https://github.com/sgvaze/osr_closed_set_all_you_need#ssb)

### Scripts
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](https://drive.google.com/drive/folders/1SLwmU5wB3wg_90W6mhbtUrJd7DTw3bsQ?usp=sharing).

## Citing this work

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}
}
```

DebGCD

DebGCD Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

DebGCD

DebGCD Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README