Table of Content

Open Access

ARTICLE

Balanced Deep Supervised Hashing

Hefei Ling1, Yang Fang1, Lei Wu1, Ping Li1,*, Jiazhong Chen1, Fuhao Zou1, Jialie Shen2
Huazhong University of Science and Technology, Wuhan, 430074, China.
Queen’s University, Belfast, United Kingdom.
* Corresponding Author: Ping Li. Email: . Email:

Computers, Materials & Continua 2019, 60(1), 85-100. https://doi.org/10.32604/cmc.2019.05588

Abstract

Recently, Convolutional Neural Network (CNN) based hashing method has achieved its promising performance for image retrieval task. However, tackling the discrepancy between quantization error minimization and discriminability maximization of network outputs simultaneously still remains unsolved. Motivated by the concern, we propose a novel Balanced Deep Supervised Hashing (BDSH) based on variant posterior probability to learn compact discriminability-preserving binary code for large scale image data. Distinguished from the previous works, BDSH can search an equilibrium point within the discrepancy. Towards the goal, a delicate objective function is utilized to maximize the discriminability of the output space with the variant posterior probability of the pair-wise label. A quantization regularizer is utilized as a relaxation from real-value outputs to the desired discrete values (e.g., -1/+1). Extensive experiments on the benchmark datasets show that our method can yield state-of-the-art image retrieval performance from various perspectives.

Keywords

Deep supervised hashing, equilibrium point, posterior probability.

Cite This Article

H. Ling, Y. Fang, L. Wu, P. Li, J. Chen et al., "Balanced deep supervised hashing," Computers, Materials & Continua, vol. 60, no.1, pp. 85–100, 2019.

Citations




This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1392

    View

  • 866

    Download

  • 0

    Like

Related articles

Share Link

WeChat scan