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

Franck Romuald Fotso Mtope, Bo Wei

Research output: Contribution to conferencePaperpeer-review

50 Downloads (Pure)

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.
Original languageEnglish
Publication statusAccepted/In press - 20 Mar 2020
EventIJCNN 2020: International Joint Conference on Neural Networks -
Duration: 19 Jul 2020 → …

Conference

ConferenceIJCNN 2020: International Joint Conference on Neural Networks
Period19/07/20 → …

Fingerprint Dive into the research topics of 'Region-DH: Region-based Deep Hashing for Multi-Instance Aware Image Retrieval'. Together they form a unique fingerprint.

Cite this