Sciweavers

NIPS
2008

Learning Hybrid Models for Image Annotation with Partially Labeled Data

13 years 5 months ago
Learning Hybrid Models for Image Annotation with Partially Labeled Data
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing partially labeled data that integrates a generative topic model for image appearance with discriminative label prediction. We propose three alternative formulations for imposing a spatial smoothness prior on the image labels. Tests of the new models and some baseline approaches on three real image datasets demonstrate the effectiveness of incorporating the latent structure.
Xuming He, Richard S. Zemel
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where NIPS
Authors Xuming He, Richard S. Zemel
Comments (0)