Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria

Christoph Straehle, Ullrich Koethe, Fred A. Hamprecht; The IEEE International Conference on Computer Vision (ICCV), 2013, pp. 1849-1856

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 cannotlink 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 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.

Related Material


[pdf]
[bibtex]
@InProceedings{Straehle_2013_ICCV,
author = {Straehle, Christoph and Koethe, Ullrich and Hamprecht, Fred A.},
title = {Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}