Home > Research > Publications & Outputs > On Aggregation of Unsupervised Deep Binary Desc...

Electronic data

  • tip_binarydesc

    Rights statement: ©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 1.27 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits

Research output: Contribution to journalJournal articlepeer-review

Published
Close
<mark>Journal publication date</mark>30/09/2020
<mark>Journal</mark>IEEE Transactions on Image Processing
Volume29
Number of pages13
Pages (from-to)9266 - 9278
Publication StatusPublished
Early online date27/09/20
<mark>Original language</mark>English

Abstract

Despite the thrilling success achieved by existing binary descriptors, most of them are still in the mire of three limitations: 1) vulnerable to the geometric transformations; 2) incapable of preserving the manifold structure when learning binary codes; 3) NO guarantee to find the true match if multiple candidates happen to have the same Hamming distance to a given query. All these together make the binary descriptor less effective, given large-scale visual recognition tasks. In this paper, we propose a novel learning-based feature descriptor, namely Unsupervised Deep Binary Descriptor (UDBD), which learns transformation invariant binary descriptors via projecting the original data and their transformed sets into a joint binary space. Moreover, we involve a ℓ2,1-norm loss term in the binary embedding process to gain simultaneously the robustness against data noises and less probability of mistakenly flipping bits of the binary descriptor, on top of it, a graph constraint is used to preserve the original manifold structure in the binary space. Furthermore, a weak bit mechanism is adopted to find the real match from candidates sharing the same minimum Hamming distance, thus enhancing matching performance. Extensive experimental results on public datasets show the superiority of UDBD in terms of matching and retrieval accuracy over state-of-the-arts.

Bibliographic note

©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.