Region Classification with Markov Field Aspect Models

Jakob Verbeek 1 William Triggs 1, 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 AI - Artificial Intelligence
LJK - Laboratoire Jean Kuntzmann
Abstract : In recent years considerable advances have been made in learning to recognize and localize visual object classes from images annotated with global image-level labels, bounding boxes, or pixel-level segmentations. A second line of research uses unsupervised learning methods such as aspect models to automatically discover the latent object classes of unlabeled image collections. Here we learn spatial aspect models from image-level labels and use them to recover labeled regions in new images. Our models combine low-level texture, color and position cues with spatial random field models that capture the local coherence of region labels. We study two spatial inference models: one based on averaging over forests of minimal spanning trees linking neighboring image regions, the other on an efficient chain-merging Expectation Propagation method for regular 8-neighbor Markov random fields. Experimental results on the MSR Cambridge data sets show that incorporating spatial terms in the aspect model significantly improves the region-level classification rates. So much so, that the spatial random field model trained from image labels only outperforms PLSA trained from segmented images.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download


https://hal.inria.fr/inria-00321129
Contributor : Jakob Verbeek <>
Submitted on : Friday, April 8, 2011 - 3:26:45 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Thursday, March 30, 2017 - 9:21:02 AM

Identifiers

Collections

Citation

Jakob Verbeek, William Triggs. Region Classification with Markov Field Aspect Models. CVPR 2007 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.383098⟩. ⟨inria-00321129v2⟩

Share

Metrics

Record views

721

Files downloads

1370