Browse by author
Lookup NU author(s): Dr Yang Long
This is the authors' accepted manuscript of an article that has been published in its final definitive form by IEEE, 2018.
For re-use rights please refer to the publisher's terms and conditions.
IEEE In order to achieve efficient similarity searching, hash functions are designed to encode images into lowdimensional binary codes with the constraint that similar features will have a short distance in the projected Hamming space. Recently, deep learning based methods have become more popular, and outperform traditional non-deep methods. However, without label information, most state-of-the-art unsupervised deep hashing algorithms suffer from severe performance degradation for unsupervised scenarios. One of the main reasons is that the adhoc encoding process cannot properly capture the visual feature distribution. In this paper, we propose a novel unsupervised framework that has two main contributions: 1) we convert the unsupervised deep hashing model into supervised by discovering pseudo labels; 2) the framework unifies likelihood maximisation, mutual information maximisation and quantisation error minimisation so that the pseudo labels can maximumly preserve the distribution of visual features. Extensive experiments on three popular datasets demonstrate the advantages of the proposed method, which leads to significant performance improvement over the state-of-the-art unsupervised hashing algorithms.
Author(s): Zhang H, Liu L, Long Y, Shao L
Publication type: Article
Publication status: Published
Journal: IEEE Transactions on Image Processing
Year: 2018
Volume: 27
Issue: 4
Pages: 1626-1638
Print publication date: 01/04/2018
Online publication date: 08/12/2017
Acceptance date: 24/11/2017
Date deposited: 17/01/2019
ISSN (print): 1057-7149
ISSN (electronic): 1941-0042
Publisher: IEEE
URL: https://doi.org/10.1109/TIP.2017.2781422
DOI: 10.1109/TIP.2017.2781422
Altmetrics provided by Altmetric
