AI RESEARCH
Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval
arXiv CS.CV
•
ArXi:2603.12711v1 Announce Type: new This paper studies unsupervised cross-domain image retrieval (UCDIR), which aims to retrieve images of the same category across different domains without relying on labeled data. Existing methods typically utilize pseudo-labels, derived from clustering algorithms, as supervisory signals for intra-domain representation learning and cross-domain feature alignment. However, these discrete pseudo-labels often fail to provide accurate and comprehensive semantic guidance.