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

Preview

Text PID6436383.pdf - Accepted Version Download (2MB) | Preview

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.

Actions (login required)

View Item

Downloads