Region-DH: Region-based Deep Hashing for Multi-Instance Aware Image Retrieval

Mtope, Franck Romuald Fotso and Wei, Bo (2020) Region-DH: Region-based Deep Hashing for Multi-Instance Aware Image Retrieval. In: 2020 International Joint Conference on Neural Networks (IJCNN 2020). Neural Networks (IJCNN) . IEEE, Piscataway, pp. 2007-2013. ISBN 9781728169279, 9781728169262

[img]
Preview
Text
PID6436383.pdf - Accepted Version

Download (2MB) | Preview
Official URL: https://doi.org/10.1109/IJCNN48605.2020.9207485

Abstract

This paper introduces an instance-aware hashing approach Region-DH for large-scale multi-label image retrieval. The accurate object bounds can significantly increase the hashing performance of instance features. We design a unified deep neural network that simultaneously localizes and recognizes objects while learning the hash functions for binary codes. Region-DH focuses on recognizing objects and building compact binary codes that represent more foreground patterns. Region-DH can flexibly be used with existing deep neural networks or more complex object detectors for image hashing. Extensive experiments are performed on benchmark datasets and show the efficacy and robustness of the proposed Region-DH model.

Item Type: Book Section
Additional Information: IJCNN 2020: International Joint Conference on Neural Networks ; Conference date: 19-07-2020
Uncontrolled Keywords: deep learning, Imaging hashing
Subjects: G400 Computer Science
G500 Information Systems
G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Rachel Branson
Date Deposited: 18 May 2020 12:26
Last Modified: 31 Jul 2021 10:18
URI: http://nrl.northumbria.ac.uk/id/eprint/43157

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics