Learning to recognize objects

Dan Roth, Ming Hsuan Yang, Narendra Ahuja

Research output: Contribution to journalConference articlepeer-review

Abstract

A learning account for the problem of object recognition is developed within the PAC (Probably Approximately Correct) model of learnability. The proposed approach makes no assumptions on the distribution of the observed objects, but quantifies success relative to its past experience. Most importantly, the success of learning an object representation is naturally tied to the ability to represent it as a function of some intermediate representations extracted from the image. We evaluate this approach in a large scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Database (COIL-100). The SNoW-based method is shown to outperform other methods in terms of recognition rates; its performance degrades gracefully when the training data contains fewer views and in the presence of occlusion noise.

Original languageEnglish (US)
Pages (from-to)724-731
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - 2000
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2000 - Hilton Head Island, SC, USA
Duration: Jun 13 2000Jun 15 2000

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Learning to recognize objects'. Together they form a unique fingerprint.

Cite this