Category-independent object proposals with diverse ranking

Ian Endres, Derek Hoiem

Research output: Contribution to journalArticlepeer-review

Abstract

We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives are completeness and diversity: Every object should have at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations by performing graph cuts based on a seed region and a learned affinity function. Then, the regions are ranked using structured learning based on various cues. Our experiments on the Berkeley Segmentation Data Set and Pascal VOC 2011 demonstrate our ability to find most objects within a small bag of proposed regions.

Original languageEnglish (US)
Article number6544186
Pages (from-to)222-234
Number of pages13
JournalIEEE transactions on pattern analysis and machine intelligence
Volume36
Issue number2
DOIs
StatePublished - Feb 1 2014

Keywords

  • Object segmentation
  • object recognition

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Category-independent object proposals with diverse ranking'. Together they form a unique fingerprint.

Cite this