DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
This addresses the need for efficient segmentation in medical imaging with weak supervision, but it is incremental as it builds on existing methods like GrabCut.
The authors tackled the problem of generating pixelwise object segmentations from bounding box annotations by proposing DeepCut, which extends GrabCut with a neural network classifier and energy minimization, achieving encouraging accuracy on fetal MRI brain and lung segmentation.
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.