Learning Hybrid Models for Image Annotation with Partially Labeled Data

Part of Advances in Neural Information Processing Systems 21 (NIPS 2008)

Bibtex »Metadata »Paper »


Xuming He, Richard Zemel


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.