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 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.
Cite
Text
Straehle et al. "Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria." International Conference on Computer Vision, 2013. doi:10.1109/ICCV.2013.232Markdown
[Straehle et al. "Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria." International Conference on Computer Vision, 2013.](https://mlanthology.org/iccv/2013/straehle2013iccv-weakly/) doi:10.1109/ICCV.2013.232BibTeX
@inproceedings{straehle2013iccv-weakly,
title = {{Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria}},
author = {Straehle, Christoph and Koethe, Ullrich and Hamprecht, Fred A.},
booktitle = {International Conference on Computer Vision},
year = {2013},
doi = {10.1109/ICCV.2013.232},
url = {https://mlanthology.org/iccv/2013/straehle2013iccv-weakly/}
}