University of British Columbia
Multiscale conditional random fields for machine vision
Abstract
dc:descriptionWe develop a single joint model which can classify images and label super-pixels, based on tree-structured conditional random fields (CRFs) derived from a hierarchical image segmentation, extending previous work by Reynolds and Murphy, and Plath and Toussaint. We show how to train this model in a weakly-supervised fashion, in which some of the images only have captions specifying which objects are present; this information is propagated down the tree and thus provides weakly labeled data at the leaves, which can be used to improve the performance of the super-pixel classifiers. After training, information can be propagated from the super-pixels up to the root-level image classifier (although this does not seem to help in practice compared to just using root-level features). We compare two kinds of tree: the standard one with pairwise potentials, and one based on noisy-or potentials, which better matches the semantics of the recursive partitioning used to create the tree. However, we do not find any significant difference between the two.
Degree
thesis:*- Name thesis:degree_name
- Master of Science - MSc
- Level thesis:degree_level
- master's
- Discipline thesis:degree_discipline
- Computer Science
- Grantor dc:publisher
- University of British Columbia
- Year dc:date
- 2010
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Duvenaud, David
Rights
dc:rights- Statement dc:rights
-
- Attribution-NonCommercial 3.0 Unported
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/2429/27032