Identification of novel classes in object class recognition

Alon Zweig, Dagan Eshar, Daphna Weinshall

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

Abstract

For novel class identification we propose to rely on the natural hierarchy of object classes, using a new approach to detect incongruent events. Here detection is based on the discrepancy between the responses of two different classifiers trained at different levels of generality: novelty is detected when the general level classifier accepts, and the specific level classifier rejects. Thus our approach is arguably more robust than traditional approaches to novelty detection, and more amendable to effective information transfer between known and new classes.We present an algorithmic implementation of this approach, show experimental results of its performance, analyze the effect of the underlying hierarchy on the task and show the benefit of using discriminative information for the training of the specific level classifier.

Original languageAmerican English
Title of host publicationDetection and Identification of Rare Audiovisual Cues
EditorsDaphna Weinshall, Jorn Anemuller, Luc Gool
Pages47-55
Number of pages9
DOIs
StatePublished - 2012

Publication series

NameStudies in Computational Intelligence
Volume384

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Identification of novel classes in object class recognition'. Together they form a unique fingerprint.

Cite this