Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
This work addresses the need for efficient and interpretable image retrieval in fine-grained scenarios, offering incremental improvements over existing methods.
The paper tackles the problem of generating attribute-aware hash codes for fine-grained image retrieval by proposing a novel method using learnable queries and an auxiliary branch to model high-order attribute interactions, resulting in improved retrieval accuracy and robustness, especially for low-bit hash codes, as demonstrated on benchmark datasets.
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.