Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval

TL;DR

This paper introduces PSCA, a two-stage prototype-based framework that enhances domain adaptive retrieval by improving semantic alignment and hash code quality through class-level prototypes and feature reconstruction.

Contribution

The proposed PSCA method innovatively combines prototype-based semantic alignment with feature reconstruction to address domain shift in retrieval tasks.

Findings

PSCA outperforms existing methods on multiple datasets.

Prototype-based semantic connections improve class separability.

Reconstructed features lead to higher quality hash codes.

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.