ConceptLearner: Discovering Visual Concepts from Weakly Labeled Image Collections release_yccr3e2k7baszfd2ttcz6rz2dm

by Bolei Zhou, Vignesh Jagadeesh, Robinson Piramuthu

Released as a article .

2014  

Abstract

Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition system, since it is expensive to obtain fully labeled data for a large number of concept categories. In this paper, we propose ConceptLearner, which is a scalable approach to discover visual concepts from weakly labeled image collections. Thousands of visual concept detectors are learned automatically, without human in the loop for additional annotation. We show that these learned detectors could be applied to recognize concepts at image-level and to detect concepts at image region-level accurately. Under domain-specific supervision, we further evaluate the learned concepts for scene recognition on SUN database and for object detection on Pascal VOC 2007. ConceptLearner shows promising performance compared to fully supervised and weakly supervised methods.
In text/plain format

Archived Files and Locations

application/pdf  2.7 MB
file_wxeddl4pmfazbhra3nxu65iwk4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2014-11-19
Version   v1
Language   en ?
arXiv  1411.5328v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d1fbe81d-8672-4b56-a102-2fcd53ed996e
API URL: JSON