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

Standard

On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits. / Wu, Gengshen; Lin, Zijia; Ding, Guiguang; Ni, Qiang; Han, Jungong.

In: IEEE Transactions on Image Processing, Vol. 29, 30.09.2020, p. 9266 - 9278.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Wu, G, Lin, Z, Ding, G, Ni, Q & Han, J 2020, 'On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits', IEEE Transactions on Image Processing, vol. 29, pp. 9266 - 9278. https://doi.org/10.1109/TIP.2020.3025437

APA

Wu, G., Lin, Z., Ding, G., Ni, Q., & Han, J. (2020). On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits. IEEE Transactions on Image Processing, 29, 9266 - 9278. https://doi.org/10.1109/TIP.2020.3025437

Vancouver

Wu G, Lin Z, Ding G, Ni Q, Han J. On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits. IEEE Transactions on Image Processing. 2020 Sep 30;29:9266 - 9278. https://doi.org/10.1109/TIP.2020.3025437

Author

Wu, Gengshen ; Lin, Zijia ; Ding, Guiguang ; Ni, Qiang ; Han, Jungong. / On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits. In: IEEE Transactions on Image Processing. 2020 ; Vol. 29. pp. 9266 - 9278.

Bibtex

@article{fd24af4400fe4cd5b2a7dbb2ca9833fc,
title = "On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits",
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.",
author = "Gengshen Wu and Zijia Lin and Guiguang Ding and Qiang Ni and Jungong Han",
note = "{\textcopyright}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. ",
year = "2020",
month = sep,
day = "30",
doi = "10.1109/TIP.2020.3025437",
language = "English",
volume = "29",
pages = "9266 -- 9278",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - On Aggregation of Unsupervised Deep Binary Descriptor with Weak Bits

AU - Wu, Gengshen

AU - Lin, Zijia

AU - Ding, Guiguang

AU - Ni, Qiang

AU - Han, Jungong

N1 - ©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.

PY - 2020/9/30

Y1 - 2020/9/30

N2 - 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.

AB - 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.

U2 - 10.1109/TIP.2020.3025437

DO - 10.1109/TIP.2020.3025437

M3 - Journal article

VL - 29

SP - 9266

EP - 9278

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

ER -