Timezone: »
Conditional Random Fields (CRFs) are an effective tool for a variety of different data segmentation and labelling tasks including visual scene interpretation, which seeks to partition images into their constituent semantic-level regions and assign appropriate class labels to each region. For accurate labelling it is important to capture the global context of the image as well as local information. We introduce a CRF based scene labelling model that incorporates both local features and features aggregated over the whole image or large sections of it. Secondly, traditional CRF learning requires fully labelled datasets. Complete labellings are typically costly and troublesome to produce. We introduce an algorithm that allows CRF models to be learned from datasets where a substantial fraction of the nodes are unlabeled. It works by marginalizing out the unknown labels so that the log-likelihood of the known ones can be maximized by gradient ascent. Loopy Belief Propagation is used to approximate the marginals needed for the gradient and log-likelihood calculations and the Bethe free-energy approximation to the log-likelihood is monitored to control the step size. Our experimental results show that incorporating top-down aggregate features significantly improves the segmentations and that effective models can be learned from fragmentary labellings. The resulting methods give scene segmentation results comparable to the state-of-the-art on three different image databases.
Author Information
Jakob Verbeek (INRIA)
Bill Triggs (CNRS)
Related Events (a corresponding poster, oral, or spotlight)
-
2007 Poster: Scene Segmentation with CRFs Learned from Partially Labeled Images »
Tue. Dec 4th 06:30 -- 06:40 PM Room
More from the Same Authors
-
2021 Spotlight: Instance-Conditioned GAN »
Arantxa Casanova · Marlene Careil · Jakob Verbeek · Michal Drozdzal · Adriana Romero Soriano -
2021 Poster: Instance-Conditioned GAN »
Arantxa Casanova · Marlene Careil · Jakob Verbeek · Michal Drozdzal · Adriana Romero Soriano -
2021 Poster: XCiT: Cross-Covariance Image Transformers »
Alaaeldin Ali · Hugo Touvron · Mathilde Caron · Piotr Bojanowski · Matthijs Douze · Armand Joulin · Ivan Laptev · Natalia Neverova · Gabriel Synnaeve · Jakob Verbeek · Herve Jegou -
2019 Spotlight: Adaptive Density Estimation for Generative Models »
Thomas Lucas · Konstantin Shmelkov · Karteek Alahari · Cordelia Schmid · Jakob Verbeek -
2016 Poster: Convolutional Neural Fabrics »
Shreyas Saxena · Jakob Verbeek -
2010 Workshop: Beyond classification: Machine Learning for next generation Computer Vision challenges »
Craig Saunders · Jakob Verbeek · Svetlana Lazebnik -
2010 Session: Spotlights Session 2 »
Bill Triggs -
2010 Session: Oral Session 1 »
Bill Triggs -
2009 Session: Oral Session 2: Images and Codes »
Bill Triggs -
2006 Poster: Randomized Clustering Forests for Building Fast and Discriminative Visual Vocabularies »
Frank Moosmann · Bill Triggs · FREDERIC JURIE