Weakly-supervised discovery of visual pattern configurations

Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka, Trevor Darrell

Research output: Contribution to journalConference articlepeer-review

121 Scopus citations

Abstract

The prominence of weakly labeled data gives rise to a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.

Original languageEnglish
Pages (from-to)1637-1645
Number of pages9
JournalAdvances in Neural Information Processing Systems
Volume2
Issue numberJanuary
StatePublished - 2014
Externally publishedYes
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: 8 Dec 201413 Dec 2014

Fingerprint

Dive into the research topics of 'Weakly-supervised discovery of visual pattern configurations'. Together they form a unique fingerprint.

Cite this