DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

@article{Rajchl2017DeepCutOS,
  title={DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks},
  author={Martin Rajchl and M. J. Lee and O. Oktay and K. Kamnitsas and J. Passerat-Palmbach and Wenjia Bai and Bernhard Kainz and D. Rueckert},
  journal={IEEE Transactions on Medical Imaging},
  year={2017},
  volume={36},
  pages={674-683}
}
  • Martin Rajchl, M. J. Lee, +5 authors D. Rueckert
  • Published 2017
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • In this paper, we propose <italic>DeepCut</italic>, a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in our case bounding boxes. [...] Key Method It extends the approach of the well-known <italic>GrabCut</italic> <xref ref-type="bibr" rid="ref1">[1]</xref> method to include machine learning by training a neural network classifier from bounding box annotations.Expand Abstract
    144 Citations
    Size-constraint loss for weakly supervised CNN segmentation
    • 2
    Pose2Seg: Detection Free Human Instance Segmentation
    • 24
    • PDF
    PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision
    Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
    • 141
    • PDF
    Weakly Supervised Deep Nuclei Segmentation using Points Annotation in Histopathology Images
    • 24
    • PDF
    Weakly supervised fully convolutional network for PET lesion segmentation
    • 3
    • PDF
    Iterative Label Denoising Network: Segmenting Male Pelvic Organs in CT From 3D Bounding Box Annotations
    • 2
    • Highly Influenced
    Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
    • 3
    • PDF
    Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
    • 211
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 53 REFERENCES
    BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
    • Jifeng Dai, Kaiming He, Jian Sun
    • Computer Science
    • 2015 IEEE International Conference on Computer Vision (ICCV)
    • 2015
    • 519
    • PDF
    From image-level to pixel-level labeling with Convolutional Networks
    • 414
    • PDF
    Conditional Random Fields as Recurrent Neural Networks
    • 1,886
    • PDF
    Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
    • 377
    • Highly Influential
    • PDF
    Multi-fold MIL Training for Weakly Supervised Object Localization
    • 193
    • PDF
    Semantic Segmentation without Annotating Segments
    • 36
    • PDF
    DenseCut: Densely Connected CRFs for Realtime GrabCut
    • 54
    • PDF
    Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
    • 2,283
    • PDF
    Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning
    • A. Vezhnevets, J. Buhmann
    • Computer Science
    • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    • 2010
    • 148
    • PDF