# Deep Ordinal Hashing with Spatial Attention

arXiv: https://arxiv.org/abs/1805.02459 · HTML: https://mlsanity.com/paper/1805.02459/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2018.

## Built on by (most cited first, 6 of 6)

- [Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition](https://mlsanity.com/paper/2112.10992/) (2021)
- [HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval](https://mlsanity.com/paper/2212.08281/) (2022)
- [Learning Label Encodings for Deep Regression](https://mlsanity.com/paper/2303.02273/) (2023)
- [An Effective Fusion Method to Enhance the Robustness of CNN](https://mlsanity.com/paper/2205.15582/) (2022)
- [CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation](https://mlsanity.com/paper/2301.06122/) (2023)
- [Deep Lifelong Cross-modal Hashing](https://mlsanity.com/paper/2304.13357/) (2023)

## Abstract (arXiv)

Hashing has attracted increasing research attentions in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature representations and hash functions learning with deep neural networks. However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images. The loss of local spatial structure makes the performance bottleneck of hash functions, therefore limiting its application for accurate similarity retrieval. In this work, we propose a novel Deep Ordinal Hashing (DOH) method, which learns ordinal representations by leveraging the ranking structure of feature space from both local and global views. In particular, to effectively build the ranking structure, we propose to learn the rank correlation space by exploiting the local spatial information from Fully Convolutional Network (FCN) and the global semantic information from the Convolutional Neural Network (CNN) simultaneously. More specifically, an effective spatial attention model is designed to capture the local spatial information by selectively learning well-specified locations closely related to target objects. In such hashing framework,the local spatial and global semantic nature of images are captured in an end-to-end ranking-to-hashing manner. Experimental results conducted on three widely-used datasets demonstrate that the proposed DOH method significantly outperforms the state-of-the-art hashing methods.