Paper Info
Title
Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria
Abstract
We propose a scheme that allows to partition an image into a previously unknown number of segments, using only minimal supervision in terms of a few must-link and cannot-link annotations. We make no use of regional data terms, learning instead what constitutes a likely boundary between segments. Since boundaries are only implicitly specified through cannot-link constraints, this is a hard and nonconvex latent variable problem. We address this problem in a greedy fashion using a randomized decision tree on features associated with interpixel edges. We use a it structured purity criterion during tree construction and also show how a backtracking strategy can be used to prevent the greedy search from ending up in poor local optima. The proposed strategy is compared with prior art on natural images.
Year
DOI
Venue
2013
10.1109/ICCV.2013.232
Computer Vision
Keywords
Field
DocType
backtracking,concave programming,decision trees,image segmentation,learning (artificial intelligence),backtracking strategy,image partitioning,image segmentation,nonconvex latent variable problem,randomized decision tree,structured purity criterion,structured split criteria,supervised learning,tree construction,decision tree,edge model,region annotation,segmentation,structured objective function,supervised learning
Information Fuzzy Networks,Decision tree,Pattern recognition,Computer science,Greedy algorithm,Supervised learning,Artificial intelligence,ID3 algorithm,Decision tree learning,Machine learning,Alternating decision tree,Incremental decision tree
Conference
Volume
Issue
ISSN
2013
1
1550-5499
Citations 
PageRank 
References 
3
0.43
28
Authors
3
Name
Order
Citations
PageRank
Christoph N. Straehle11277.57
Ullrich Koethe224922.37
Fred A. Hamprecht396276.24