Learning discriminative collections of part detectors for object recognition

Kevin J. Shih, Ian Endres, Derek Hoiem

Research output: Contribution to journalArticlepeer-review


We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC2010, we evaluate the part detectors' ability to discriminate and localize annotated keypoints and their effectiveness in detecting object categories.

Original languageEnglish (US)
Article number2366122
Pages (from-to)1571-1584
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number8
StatePublished - Aug 1 2015


  • Discriminative parts
  • Object recognition
  • Part sharing

ASJC Scopus subject areas

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


Dive into the research topics of 'Learning discriminative collections of part detectors for object recognition'. Together they form a unique fingerprint.

Cite this