Learning transformation-invariant local descriptors with low-coupling binary codes

Miao, Y., Lin, Z., Ma, X. ORCID: 0000-0003-1318-3590, Ding, G. and Han, J., 2021. Learning transformation-invariant local descriptors with low-coupling binary codes. IEEE Transactions on Image Processing, 30, pp. 7554-7566. ISSN 1057-7149

1524144_Ma.pdf - Post-print

Download (779kB) | Preview


Despite the great success achieved by prevailing binary local descriptors, they are still suffering from two problems: 1) vulnerable to the geometric transformations; 2) lack of an effective treatment to the highly-correlated bits that are generated by directly applying the scheme of image hashing. To tackle both limitations, we propose an unsupervised Transformation-invariant Binary Local Descriptor learning method (TBLD). Specifically, the transformation invariance of binary local descriptors is ensured by projecting the original patches and their transformed counterparts into an identical high-dimensional feature space and an identical low-dimensional descriptor space simultaneously. Meanwhile, it enforces the dissimilar image patches to have distinctive binary local descriptors. Moreover, to reduce high correlations between bits, we propose a bottom-up learning strategy, termed Adversarial Constraint Module , where low-coupling binary codes are introduced externally to guide the learning of binary local descriptors. With the aid of the Wasserstein loss, the framework is optimized to encourage the distribution of the generated binary local descriptors to mimic that of the introduced low-coupling binary codes, eventually making the former more low-coupling. Experimental results on three benchmark datasets well demonstrate the superiority of the proposed method over the state-of-the-art methods.

Item Type: Journal article
Publication Title: IEEE Transactions on Image Processing
Creators: Miao, Y., Lin, Z., Ma, X., Ding, G. and Han, J.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Volume: 30
ISSN: 1057-7149
34449360PubMed ID
Rights: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions: Schools > Nottingham Business School
Record created by: Jeremy Silvester
Date Added: 10 Mar 2022 13:02
Last Modified: 10 Mar 2022 13:02
URI: https://irep.ntu.ac.uk/id/eprint/45844

Actions (login required)

Edit View Edit View


Views per month over past year


Downloads per month over past year