Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning



Do, Thanh-Toan ORCID: 0000-0002-6249-0848, Le, Khoa, Hoang, Tuan, Le, Huu, Nguyen, Tam V and Cheung, Ngai-Man
(2019) Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning. IEEE Transactions on Image Processing, 28 (10). pp. 4954-4969.

[img] Text
SAH.pdf - Author Accepted Manuscript

Download (4MB) | Preview

Abstract

Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently. Hence, these frameworks may generate suboptimal hash codes. In this paper, we first propose a novel unsupervised hashing framework in which feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization generates aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, the proposed method is flexible. It can be extended for supervised hashing. When the data label is available, the framework can be adapted to learn binary codes which minimize the reconstruction loss with respect to label vectors. Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks. Extensive experiments on benchmark datasets under various settings show that the proposed methods outperform the state-of-the-art unsupervised and supervised hashing methods.

Item Type: Article
Uncontrolled Keywords: Binary codes, Optimization, Feature extraction, Hash functions, Quantization (signal), Image reconstruction, Training
Depositing User: Symplectic Admin
Date Deposited: 23 May 2019 15:50
Last Modified: 14 Mar 2023 07:38
DOI: 10.1109/TIP.2019.2913509
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3042550