Localizing Objects While Learning Their Appearance

Thomas Deselaers, Bogdan Alexe, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning a new object class from cluttered training images is very challenging when the location of object instances is unknown. Previous works generally require objects covering a large portion of the images. We present a novel approach that can cope with extensive clutter as well as large scale and appearance variations between object instances. To make this possible we propose a conditional random field that starts from generic knowledge and then progressively adapts to the new class. Our approach simultaneously localizes object instances while learning an appearance model specific for the class. We demonstrate this on the challenging Pascal VOC 2007 dataset. Furthermore, our method enables to train any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2010
Subtitle of host publication11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV
EditorsKostas Daniilidis, Petros Maragos, Nikos Paragios
PublisherSpringer
Pages452-466
Number of pages15
ISBN (Electronic)978-3-642-15561-1
ISBN (Print)978-3-642-15560-4
DOIs
Publication statusPublished - 2010

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume6314
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Fingerprint

Dive into the research topics of 'Localizing Objects While Learning Their Appearance'. Together they form a unique fingerprint.

Cite this