Simultaneous Region Localization and Hash Coding for Fine-grained Image Retrieval

TL;DR

This paper introduces a deep learning approach that simultaneously localizes discriminative regions and generates hash codes for fine-grained image retrieval, improving accuracy without requiring bounding-box annotations.

Contribution

It proposes a joint framework with region localization and hash coding modules that mutually reinforce each other, capturing subtle differences at multiple scales.

Findings

Significant performance improvements over existing fine-grained hashing methods

Effective localization of discriminative regions without bounding-box annotations

Enhanced retrieval accuracy on benchmark datasets

Abstract

Fine-grained image hashing is a challenging problem due to the difficulties of discriminative region localization and hash code generation. Most existing deep hashing approaches solve the two tasks independently. While these two tasks are correlated and can reinforce each other. In this paper, we propose a deep fine-grained hashing to simultaneously localize the discriminative regions and generate the efficient binary codes. The proposed approach consists of a region localization module and a hash coding module. The region localization module aims to provide informative regions to the hash coding module. The hash coding module aims to generate effective binary codes and give feedback for learning better localizer. Moreover, to better capture subtle differences, multi-scale regions at different layers are learned without the need of bounding-box/part annotations. Extensive experiments are conducted on two public benchmark fine-grained datasets. The results demonstrate significant improvements in the performance of our method relative to other fine-grained hashing algorithms.