Deep Hashing with Triplet Labels and Unification Binary Code Selection for Fast Image Retrieval

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

3 Scopus Citations
View graph of relations

Author(s)

  • Wilson Y. F. Yuen
  • Peter H. W. Wong
  • Hon-Tung Luk
  • Kin Wai Lau
  • Hok Kwan Cheung

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationMultiMedia Modeling
Subtitle of host publicationProceedings, Part I
EditorsIoannis Kompatsiaris, Benoit Huet, Vasileios Mezaris, Cathal Gurrin, Wen-Huang Cheng, Stefanos Vrochidis
PublisherSpringer Nature Switzerland AG
Pages277-288
ISBN (electronic)9783030057107
ISBN (print)9783030057091
Publication statusPublished - 2019

Publication series

NameLecture Notes in Computer Science
Volume11295
ISSN (Print)0302-9743
ISSN (electronic)1611-3349

Conference

Title25th International Conference on MultiMedia Modeling, MMM 2019
PlaceGreece
CityThessaloniki
Period8 - 11 January 2019

Abstract

With the significant breakthrough of computer vision using convolutional neural networks, deep learning has been applied to image hashing algorithms for efficient image retrieval on large-scale datasets. Inspired by Deep Supervised Hashing (DSH) algorithm, we propose to use triplet loss function with an online training strategy that takes three images as training inputs to learn compact binary codes. A relaxed triplet loss function is designed to maximize the discriminability with consideration of the balance property of the output space. In addition, a novel unification binary code selection algorithm is also proposed to represent the scalable binary code in an efficient way, which can fix the problem of conventional deep hashing methods that generate different lengths of binary code by retraining. Experiments on two well-known datasets of CIFAR-10 and NUS-WIDE show that the proposed DSH with use of unification binary code selection can achieve promising performance as compared with conventional image hashing and CNN-based hashing algorithms.

Research Area(s)

  • Deep hashing, Triplet loss, Unification binary code selection

Citation Format(s)

Deep Hashing with Triplet Labels and Unification Binary Code Selection for Fast Image Retrieval. / Zhou, Chang; Po, Lai-Man; Liu, Mengyang et al.
MultiMedia Modeling: Proceedings, Part I. ed. / Ioannis Kompatsiaris; Benoit Huet; Vasileios Mezaris; Cathal Gurrin; Wen-Huang Cheng; Stefanos Vrochidis. Springer Nature Switzerland AG, 2019. p. 277-288 (Lecture Notes in Computer Science; Vol. 11295).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review