Deep learning based supervised hashing for efficient image retrieval

Viet Anh Nguyen, Minh N. Do

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Due to its storage and search efficiency, hashing has attracted great attentions in large-scale vision problems such as image retrieval and recognition. This paper presents a novel Deep Learning based Supervised Hashing (DLSH) method by using a deep neural network to better capture the semantic structure of nonlinear and complex data. We consider learning a nonlinear embedding that simultaneously preserves semantic information and produces nearby binary codes for semantically similar data. Specifically, our hashing model is trained to maximize the similarity measure of neighbor pairs while preserving the relative similarity of non-neighbor pairs with a relaxed empirical penalty in the binary space. An effective regularizer for minimizing the quantization loss between the learned embedding and the binary codes is also considered in the optimization to generate better hash code quality. Experimental results have demonstrated the proposed method outperforms the state-of-the-art methods.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Multimedia and Expo, ICME 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781467372589
DOIs
StatePublished - Aug 25 2016
Event2016 IEEE International Conference on Multimedia and Expo, ICME 2016 - Seattle, United States
Duration: Jul 11 2016Jul 15 2016

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2016-August
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Other

Other2016 IEEE International Conference on Multimedia and Expo, ICME 2016
CountryUnited States
CitySeattle
Period7/11/167/15/16

Fingerprint

Binary codes
Image retrieval
Semantics
Image recognition
Deep learning
Deep neural networks

Keywords

  • deep learning
  • image retrieval
  • semantic hashing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Nguyen, V. A., & Do, M. N. (2016). Deep learning based supervised hashing for efficient image retrieval. In 2016 IEEE International Conference on Multimedia and Expo, ICME 2016 [7552927] (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/ICME.2016.7552927

Deep learning based supervised hashing for efficient image retrieval. / Nguyen, Viet Anh; Do, Minh N.

2016 IEEE International Conference on Multimedia and Expo, ICME 2016. IEEE Computer Society, 2016. 7552927 (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2016-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nguyen, VA & Do, MN 2016, Deep learning based supervised hashing for efficient image retrieval. in 2016 IEEE International Conference on Multimedia and Expo, ICME 2016., 7552927, Proceedings - IEEE International Conference on Multimedia and Expo, vol. 2016-August, IEEE Computer Society, 2016 IEEE International Conference on Multimedia and Expo, ICME 2016, Seattle, United States, 7/11/16. https://doi.org/10.1109/ICME.2016.7552927
Nguyen VA, Do MN. Deep learning based supervised hashing for efficient image retrieval. In 2016 IEEE International Conference on Multimedia and Expo, ICME 2016. IEEE Computer Society. 2016. 7552927. (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2016.7552927
Nguyen, Viet Anh ; Do, Minh N. / Deep learning based supervised hashing for efficient image retrieval. 2016 IEEE International Conference on Multimedia and Expo, ICME 2016. IEEE Computer Society, 2016. (Proceedings - IEEE International Conference on Multimedia and Expo).
@inproceedings{efdc62c75320448291345b47d7b119ed,
title = "Deep learning based supervised hashing for efficient image retrieval",
abstract = "Due to its storage and search efficiency, hashing has attracted great attentions in large-scale vision problems such as image retrieval and recognition. This paper presents a novel Deep Learning based Supervised Hashing (DLSH) method by using a deep neural network to better capture the semantic structure of nonlinear and complex data. We consider learning a nonlinear embedding that simultaneously preserves semantic information and produces nearby binary codes for semantically similar data. Specifically, our hashing model is trained to maximize the similarity measure of neighbor pairs while preserving the relative similarity of non-neighbor pairs with a relaxed empirical penalty in the binary space. An effective regularizer for minimizing the quantization loss between the learned embedding and the binary codes is also considered in the optimization to generate better hash code quality. Experimental results have demonstrated the proposed method outperforms the state-of-the-art methods.",
keywords = "deep learning, image retrieval, semantic hashing",
author = "Nguyen, {Viet Anh} and Do, {Minh N.}",
year = "2016",
month = "8",
day = "25",
doi = "10.1109/ICME.2016.7552927",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",
booktitle = "2016 IEEE International Conference on Multimedia and Expo, ICME 2016",

}

TY - GEN

T1 - Deep learning based supervised hashing for efficient image retrieval

AU - Nguyen, Viet Anh

AU - Do, Minh N.

PY - 2016/8/25

Y1 - 2016/8/25

N2 - Due to its storage and search efficiency, hashing has attracted great attentions in large-scale vision problems such as image retrieval and recognition. This paper presents a novel Deep Learning based Supervised Hashing (DLSH) method by using a deep neural network to better capture the semantic structure of nonlinear and complex data. We consider learning a nonlinear embedding that simultaneously preserves semantic information and produces nearby binary codes for semantically similar data. Specifically, our hashing model is trained to maximize the similarity measure of neighbor pairs while preserving the relative similarity of non-neighbor pairs with a relaxed empirical penalty in the binary space. An effective regularizer for minimizing the quantization loss between the learned embedding and the binary codes is also considered in the optimization to generate better hash code quality. Experimental results have demonstrated the proposed method outperforms the state-of-the-art methods.

AB - Due to its storage and search efficiency, hashing has attracted great attentions in large-scale vision problems such as image retrieval and recognition. This paper presents a novel Deep Learning based Supervised Hashing (DLSH) method by using a deep neural network to better capture the semantic structure of nonlinear and complex data. We consider learning a nonlinear embedding that simultaneously preserves semantic information and produces nearby binary codes for semantically similar data. Specifically, our hashing model is trained to maximize the similarity measure of neighbor pairs while preserving the relative similarity of non-neighbor pairs with a relaxed empirical penalty in the binary space. An effective regularizer for minimizing the quantization loss between the learned embedding and the binary codes is also considered in the optimization to generate better hash code quality. Experimental results have demonstrated the proposed method outperforms the state-of-the-art methods.

KW - deep learning

KW - image retrieval

KW - semantic hashing

UR - http://www.scopus.com/inward/record.url?scp=84987621251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987621251&partnerID=8YFLogxK

U2 - 10.1109/ICME.2016.7552927

DO - 10.1109/ICME.2016.7552927

M3 - Conference contribution

AN - SCOPUS:84987621251

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

BT - 2016 IEEE International Conference on Multimedia and Expo, ICME 2016

PB - IEEE Computer Society

ER -