Fully Unsupervised Domain-Agnostic Image Retrieval
- 20 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (6) , 5077-5090
Abstract
Recent research in cross-domain image retrieval has focused on addressing two challenging issues: handling domain variations in the data and dealing with the lack of sufficient training labels. However, these problems have often been studied separately, limiting the practicality and significance of the research outcomes. The existing cross-domain setting is also restricted to cases where domain labels are known during training, and all samples have semantic category information or instance correspondences. In this paper, we propose a novel approach to address a more general and practical problem: fully unsupervised domain-agnostic image retrieval under the domain-unknown setting, where no annotations are provided. Our approach tackles both the domain variation and missing labels challenges simultaneously. We introduce a new fully unsupervised One-Shot Synthesis-based Contrastive learning method (termed OSSCo) to project images from different data distributions into a shared feature space for similarity measurement. To handle the domain-unknown setting, we propose One-Shot unpaired image-to-image Translation (OST) between a randomly selected one-shot image and the rest of the training images. By minimizing the global distance between the original images and the generated images from OST, the model learns domain-agnostic representations. To address the label-unknown setting, we employ contrastive learning with a synthesis-based transform module from the OST training. This allows for effective representation learning without any annotations or external constraints. We evaluate our proposed method on diverse datasets, and the results demonstrate its effectiveness. Notably, our approach achieves comparable performance to current state-of-the-art supervised methods.Keywords
Funding Information
- National Natural Science Foundation of China (U20B2063, 62220106008 and 62306067)
This publication has 57 references indexed in Scilit:
- DaCo: domain-agnostic contrastive learning for visual place recognitionApplied Intelligence, 2023
- MoDA: Map Style Transfer for Self-supervised Domain Adaptation of Embodied Agents2022
- TSIT: A Simple and Versatile Framework for Image-to-Image Translation2020
- ForkGAN: Seeing into the Rainy Night2020
- Self-supervising Fine-Grained Region Similarities for Large-Scale Image Localization2020
- Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training2018
- Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding2018
- CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples2016
- Microsoft COCO: Common Objects in Context2014
- SURF: Speeded Up Robust Features2006