In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.
@article{arxiv.1605.07866,
title = {DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks},
author = {Martin Rajchl and Matthew C. H. Lee and Ozan Oktay and Konstantinos Kamnitsas and Jonathan Passerat-Palmbach and Wenjia Bai and Mellisa Damodaram and Mary A. Rutherford and Joseph V. Hajnal and Bernhard Kainz and Daniel Rueckert},
journal= {arXiv preprint arXiv:1605.07866},
year = {2016}
}