Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization

2025-09-21

AI Summary

To address the lack of semantic interpretability and cross-class discriminability in hash codes for fine-grained image retrieval, this paper proposes an attribute-aware learnable query hashing method. The method introduces learnable visual attribute queries, wherein each hash bit explicitly corresponds to a semantically meaningful attribute; incorporates an auxiliary branch to model higher-order attribute interactions, thereby enhancing the discriminability and robustness of low-bit hash codes; and employs a Transformer architecture with multi-head self-attention for end-to-end optimization. Evaluated on standard benchmarks—including CUB-200 and Stanford Dogs—the method significantly outperforms state-of-the-art hashing approaches, particularly under 16–32-bit code lengths, achieving substantial gains in retrieval accuracy. Crucially, it simultaneously delivers strong semantic interpretability—each bit is grounded in human-understandable attributes—and high retrieval performance.

Technology Category

• Computer Vision: Image and Video Retrieval
• Search and Optimization: Learning to Search
• Machine Learning: Representation Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• 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

Fine-grained hashing has become a powerful solution for rapid and efficient image retrieval, particularly in scenarios requiring high discrimination between visually similar categories. To enable each hash bit to correspond to specific visual attributes, we propoe a novel method that harnesses learnable queries for attribute-aware hash codes learning. This method deploys a tailored set of queries to capture and represent nuanced attribute-level information within the hashing process, thereby enhancing both the interpretability and relevance of each hash bit. Building on this query-based optimization framework, we incorporate an auxiliary branch to help alleviate the challenges of complex landscape optimization often encountered with low-bit hash codes. This auxiliary branch models high-order attribute interactions, reinforcing the robustness and specificity of the generated hash codes. Experimental results on benchmark datasets demonstrate that our method generates attribute-aware hash codes and consistently outperforms state-of-the-art techniques in retrieval accuracy and robustness, especially for low-bit hash codes, underscoring its potential in fine-grained image hashing tasks.

Problem

• Learning attribute-aware hash codes for fine-grained image retrieval
• Optimizing low-bit hash codes for visually similar categories
• Enhancing interpretability and specificity of hash bits

Innovation

• Uses learnable queries for attribute-aware hash codes
• Incorporates auxiliary branch for high-order attribute interactions
• Optimizes low-bit hash codes for fine-grained retrieval