Object Discovery and Localization Via Structural Contrast

Shuanglu Dai, Pengyu Su, Hong Man

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper explores structural contrast of object proposal for unsupervised object discovery. In this paper, an object proposal is considered as distinctive to the others in an image based on the structural uniqueness and distribution. A symmetric Kullback-Leibler (KL) distance metric is proposed to measure the difference between the distributions of structured edges. The computation of this distance metric is fully unsupervised, without any image level annotation or any labeling of visual semantics. Inspired by the pixel-level saliency filtering, a contrast-based saliency assignment is introduced to model the uniqueness and distribution distinctiveness of an object proposal as structural contrast. Visual objects can be discovered and localized by the proposals with the highest ranked structural contrast. Experiments evaluated on PascaiVOC07 demonstrate that the proposed unsupervised method outperforms the state-of-the-art unsupervised and weakly-supervised methods.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
Pages2760-2764
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - 29 Aug 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 7 Oct 201810 Oct 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
Country/TerritoryGreece
CityAthens
Period7/10/1810/10/18

Keywords

  • Object discovery
  • Object proposal
  • Proposal Saliency
  • Structural contrast

Fingerprint

Dive into the research topics of 'Object Discovery and Localization Via Structural Contrast'. Together they form a unique fingerprint.

Cite this