Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrieval

--Unsupervised efficient domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, while maintaining low storage cost and high retrieval efficiency. However, existing methods typically fail to address potential noise in the target domain, and directly align high-level features across domains, thus resulting in suboptimal retrieval performance. T o address these challenges, we propose a novel Cross-Domain Diffusion with Progressive Alignment method (COUPLE). This approach revisits unsupervised efficient domain adaptive retrieval from a graph diffusion perspective, simulating cross-domain adaptation dynamics to achieve a stable target domain adaptation process. First, we construct a cross-domain relationship graph and leverage noise-robust graph flow diffusion to simulate the transfer dynamics from the source domain to the target domain, identifying lower noise clusters. Furthermore, we employ a hierarchical Mixup operation for progressive domain alignment, which is performed along the cross-domain random walk paths. Utilizing target domain discriminative hash learning and progressive domain alignment, COUPLE enables effective domain adaptive hash learning. Extensive experiments demonstrate COUPLE's effectiveness on competitive benchmarks. PPROXIMA TE nearest neighbor (ANN) [1], [2] search, which aims to efficiently find data samples in a dataset that are close to a given query sample within an acceptable margin of error, has garnered significant attention due to its wide range of applications, e.g., image retrieval [3], [4], search engines [5], recommender system [6] and retrieval-augmented generation (RAG) [7], [8]. Hash-based ANN retrieval [9]-[13] offers higher efficiency and lower storage costs by replacing computationally expensive pairwise distance calculations with bit-wise XOR and bit-counting operations [14]. Junyu Luo, Y usheng Zhao, Wei Ju, Ming Zhang are with State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China. Xiao Luo is with Department of Computer Science, University of California, Los Angeles, USA. Zhiping Xiao is with Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, USA. Li Shen is with JD Explore Academy.