UBC Theses and Dissertations

UBC Theses Logo

UBC Theses and Dissertations

Multiscale conditional random fields for machine vision Duvenaud, David

Abstract

We 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.

Item Media

Item Citations and Data

Rights

Attribution-NonCommercial 3.0 Unported