Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2011

Abstract

A common obstacle in effective learning of visual concept classifiers is the scarcity of positive training examples due to expensive labeling cost. This paper explores the sampling of weakly tagged web images for concept learning without human assistance. In particular, ontology knowledge is incorporated for semantic pooling of positive examples from ontologically neighboring concepts. This effectively widens the coverage of the positive samples with visually more diversified content, which is important for learning a good concept classifier. We experiment with two learning strategies: aggregate and incremental. The former strategy re-trains a new classifier by combining existing and newly collected examples, while the latter updates the existing model using the new samples incrementally. Extensive experiments on NUS-WIDE and VOC 2010 datasets show very encouraging results, even when comparing with classifiers learnt using expert labeled training examples.

Keywords

Semantic pooling; Training set construction; Visual concepts

Discipline

Data Storage Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11, Scottsdale, Arizona, November 28 - December 1

First Page

1045

Last Page

1048

ISBN

9781450306164

Identifier

10.1145/2072298.2071934

Publisher

ACM

City or Country

Scottsdale, Arizona

Download

Share

COinS