Unsupervised Cross-domain Image Retrieval Via Prototypical Optimal Transport

Abstract

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the same category across diverse domains without relying on labeled data. Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment. However, these segregated strategies overlook the potential synergies between these tasks. This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework. ProtoOT leverages the strengths of the K-means clustering method to effectively manage distribution imbalances inherent in UCIR. By utilizing K-means for generating initial prototypes and approximating class marginal distributions, we modify the constraints in Optimal Transport accordingly, significantly enhancing its performance in UCIR scenarios. Furthermore, we incorporate con

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keyli2024unsupervised

Related papers

• A Unified Optimal Transport Framework For Cross-modal Retrieval With Noisy Labels (2024)5.24
• DUDE: Diffusion-based Unsupervised Cross-domain Image Retrieval (2025)0.00
• Test-time Training For Data-efficient UCDR (2022)0.00
• Dual-view Curricular Optimal Transport For Cross-lingual Cross-modal Retrieval (2023)9.03
• Text-phase Synergy Network With Dual Priors For Unsupervised Cross-domain Image Retrieval (2026)0.00
• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Correspondence-free Domain Alignment For Unsupervised Cross-domain Image Retrieval (2023)9.23