Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval

2025-12-04

AI Summary

To address three key challenges in domain-adaptive hashing retrieval—cross-domain semantic inconsistency, unreliable pseudo-labels, and low-quality hash codes—this paper proposes a two-stage framework. In the first stage, orthogonal prototype learning is introduced to achieve class-level semantic alignment, overcoming the limitations of conventional pairwise sample alignment. In the second stage, pseudo-label reliability is measured via geometric proximity, and domain-specific quantization functions are jointly optimized with mutual approximation constraints within a reconstructed feature space to enhance hash consistency. The method integrates prototype-driven alignment, reliability-weighted pseudo-label refinement, and reconstructed-feature quantization. Extensive experiments on multiple cross-domain image retrieval benchmarks demonstrate significant improvements over state-of-the-art methods, effectively mitigating domain shift and validating the efficacy of synergistic optimization between semantic alignment and reliable quantization.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations: 1) neglecting class-level semantic alignment and excessively pursuing pair-wise sample alignment; 2) lacking either pseudo-label reliability consideration or geometric guidance for assessing label correctness; 3) directly quantizing original features affected by domain shift, undermining the quality of learned hash codes. In view of these limitations, we propose Prototype-Based Semantic Consistency Alignment (PSCA), a two-stage framework for effective domain adaptive retrieval. In the first stage, a set of orthogonal prototypes directly establishes class-level semantic connections, maximizing inter-class separability while gathering intra-class samples. During the prototype learning, geometric proximity provides a reliability indicator for semantic consistency alignment through adaptive weighting of pseudo-label confidences. The resulting membership matrix and prototypes facilitate feature reconstruction, ensuring quantization on reconstructed rather than original features, thereby improving subsequent hash coding quality and seamlessly connecting both stages. In the second stage, domain-specific quantization functions process the reconstructed features under mutual approximation constraints, generating unified binary hash codes across domains. Extensive experiments validate PSCA's superior performance across multiple datasets.

Problem

• Aligns class-level semantics across domains for retrieval
• Ensures pseudo-label reliability with geometric guidance
• Improves hash code quality via feature reconstruction before quantization

Innovation

• Orthogonal prototypes establish class-level semantic connections
• Geometric proximity weights pseudo-label confidence for alignment
• Feature reconstruction before quantization improves hash code quality