Learning discriminative and shareable patches for scene classification

Shoucheng Ni, Qieshi Zhangg, Seiichiro Kamata, Chongyang Zhang

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

2 Citations (Scopus)

Abstract

This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1317-1321
Number of pages5
Volume2016-May
ISBN (Electronic)9781479999880
DOIs
Publication statusPublished - 2016 May 18
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: 2016 Mar 202016 Mar 25

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period16/3/2016/3/25

Fingerprint

Neural networks

Keywords

  • deep-learned patch feature
  • Learning discriminative and shareable patches
  • scene classification

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Ni, S., Zhangg, Q., Kamata, S., & Zhang, C. (2016). Learning discriminative and shareable patches for scene classification. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 1317-1321). [7471890] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7471890

Learning discriminative and shareable patches for scene classification. / Ni, Shoucheng; Zhangg, Qieshi; Kamata, Seiichiro; Zhang, Chongyang.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 1317-1321 7471890.

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

Ni, S, Zhangg, Q, Kamata, S & Zhang, C 2016, Learning discriminative and shareable patches for scene classification. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7471890, Institute of Electrical and Electronics Engineers Inc., pp. 1317-1321, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 16/3/20. https://doi.org/10.1109/ICASSP.2016.7471890
Ni S, Zhangg Q, Kamata S, Zhang C. Learning discriminative and shareable patches for scene classification. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1317-1321. 7471890 https://doi.org/10.1109/ICASSP.2016.7471890
Ni, Shoucheng ; Zhangg, Qieshi ; Kamata, Seiichiro ; Zhang, Chongyang. / Learning discriminative and shareable patches for scene classification. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1317-1321
@inproceedings{fa464cc63df848559ee6298c278ccdec,
title = "Learning discriminative and shareable patches for scene classification",
abstract = "This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.",
keywords = "deep-learned patch feature, Learning discriminative and shareable patches, scene classification",
author = "Shoucheng Ni and Qieshi Zhangg and Seiichiro Kamata and Chongyang Zhang",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/ICASSP.2016.7471890",
language = "English",
volume = "2016-May",
pages = "1317--1321",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Learning discriminative and shareable patches for scene classification

AU - Ni, Shoucheng

AU - Zhangg, Qieshi

AU - Kamata, Seiichiro

AU - Zhang, Chongyang

PY - 2016/5/18

Y1 - 2016/5/18

N2 - This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.

AB - This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.

KW - deep-learned patch feature

KW - Learning discriminative and shareable patches

KW - scene classification

UR - http://www.scopus.com/inward/record.url?scp=84973367427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973367427&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7471890

DO - 10.1109/ICASSP.2016.7471890

M3 - Conference contribution

VL - 2016-May

SP - 1317

EP - 1321

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -