Hu, Conghui, Can Zhang, and Gim Hee Lee. “Unsupervised feature representation learning for domain-generalized cross-domain image retrieval.” Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.
Paper Link: ICCV 2023
Introduction
This work addresses domain-generalized cross-domain image retrieval through unsupervised feature representation learning. The method aims to learn robust features that generalize across multiple domains.
Key Contributions
- Domain generalization approach for cross-domain retrieval
- Unsupervised feature learning framework
- Generalization across multiple unseen domains
Methodology
The proposed framework learns domain-generalized features that can be effectively used for retrieval across different domains without domain-specific adaptation.
Figures
Note: This paper was published at ICCV 2023. Images will be added once the arXiv version is available or from the conference proceedings.
Results
Experimental results show improved generalization performance across various domain shifts in image retrieval tasks.