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

3 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

Keywords

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

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Learning discriminative and shareable patches for scene classification'. Together they form a unique fingerprint.

  • 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