DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSemantic SegmentationSimilar Papers 제목 키워드 기반
Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
We propose a novel weakly supervised learning segmentation based on several global constraints derived from box annotations. Particularly, we leverage a classical tightness prior to a deep learning setting via imposing a…
Weakly-supervised LearningWeakly supervised segmentationAutomatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
Accurate segmentation for medical images is important for clinical diagnosis. Existing automatic segmentation methods are mainly based on fully supervised learning and have an extremely high demand for precise annotation…
ClusteringSegmentationWeakly-supervised LearningMOTS: Multi-Object Tracking and Segmentation
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-au…
Multi-Object TrackingMulti-Object Tracking and SegmentationMultiple Object TrackingObject+2Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object bou…
ObjectSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1Coarse-to-fine Semantic Segmentation from Image-level Labels
Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most …
Foreground SegmentationObjectSegmentationSemantic Segmentation