Awesome

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

Introduction

This repository contains the code for the paper <a href="https://arxiv.org/abs/2403.14410">GLC++ </a>, which is a substantial extension of our CVPR 2023 paper <a href="https://arxiv.org/abs/2303.07110">GLC</a>.

Despite the simple global and local clustering (GLC) technique achieving commendable performance in separating "known" and "unknown" data, its reliance on pseudo-labeling supervision, especially using uniform encoding for all "unknown" data limits its capacity to discriminate among different "unknown" categories. To alleviate this, we promote GLC to GLC++ by developing a new contrastive affinity learning strategy, sidestepping the need for a specialized source model structure. Remarkably, in the most challenging open-partial-set scenarios on VisDA, GLC++ boosts up the H-score from 73.1% to 75.0%. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies, e.g., OVANet and UMAD.

Framework

Prerequisites

• python3, pytorch, numpy, PIL, scipy, sklearn, tqdm, etc.
• We have presented the our conda environment file in ./environment.yml.

Dataset

We have conducted extensive expeirments on four datasets with three category shift scenario, i.e., Partial-set DA (PDA), Open-set DA (OSDA), and Open-partial DA (OPDA). The following is the details of class split for each scenario. Here, $\mathcal{Y}$, $\mathcal{\bar{Y}_s}$, and $\mathcal{\bar{Y}_t}$ denotes the source-target-shared class, the source-private class, and the target-private class, respectively.

Please manually download these datasets from the official websites, and unzip them to the ./data folder. To ease your implementation, we have provide the image_unida_list.txt for each dataset subdomains.

./data
├── Office
│   ├── Amazon
|       ├── ...
│       ├── image_unida_list.txt
│   ├── Dslr
|       ├── ...
│       ├── image_unida_list.txt
│   ├── Webcam
|       ├── ...
│       ├── image_unida_list.txt
├── OfficeHome
│   ├── ...
├── VisDA
│   ├── ...

Training

1. Open-partial Domain Adaptation (OPDA) on Office, OfficeHome, and VisDA

# Source Model Preparing
bash ./scripts/train_source_OPDA.sh
# Target Model Adaptation
bash ./scripts/train_target_OPDA.sh

2. Open-set Domain Adaptation (OSDA) on Office, OfficeHome, and VisDA

# Source Model Preparing
bash ./scripts/train_source_OSDA.sh
# Target Model Adaptation
bash ./scripts/train_target_OSDA.sh

3. Partial-set Domain Adaptation (PDA) on Office, OfficeHome, and VisDA

# Source Model Preparing
bash ./scripts/train_source_PDA.sh
# Target Model Adaptation
bash ./scripts/train_target_PDA.sh

Citation

If you find our codebase helpful, please star our project and cite our paper:

@article{sanqing2024GLC_PLUS,
  title={GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning},
  author={Qu, Sanqing and Zou, Tianpei and Röhrbein, Florian and Lu, Cewu and Chen, Guang and Tao, Dacheng and Jiang, Changjun},
  journal={arXiv preprint arXiv:2403.14410},
  year={2024}
}

@inproceedings{sanqing2023GLC,
  title={Upcycling Models under Domain and Category Shift},
  author={Qu, Sanqing and Zou, Tianpei and Röhrbein, Florian and Lu, Cewu and Chen, Guang and Tao, Dacheng and Jiang, Changjun},
  booktitle={CVPR},
  year={2023},
}

Contact

• sanqingqu@gmail.com or 2011444@tongji.edu.cn