Poster
Learning Hybrid Models for Image Annotation with Partially Labeled Data
Xuming He · Richard Zemel

Tue Dec 9th 07:30 PM -- 12:00 AM @ None #None

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 two real image datasets demonstrate the effectiveness of incorporating the latent structure.

Author Information

Xuming He (National ICT Australia)
Richard Zemel (Vector Institute/University of Toronto)

More from the Same Authors