ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

@article{Lin2016ScribbleSupSC,
  title={ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation},
  author={Di Lin and Jifeng Dai and J. Jia and Kaiming He and Jian Sun},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={3159-3167}
}
  • Di Lin, Jifeng Dai, +2 authors Jian Sun
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure. [...] Key Method Our algorithm is based on a graphical model that jointly propagates information from scribbles to unmarked pixels and learns network parameters. We present competitive object semantic segmentation results on the PASCAL VOC dataset by using scribbles as annotations. Scribbles are also favored for annotating stuff (e.g., water, sky, grass…Expand Abstract
    Boundary Perception Guidance: A Scribble-Supervised Semantic Segmentation Approach
    • 6
    • Highly Influenced
    • Open Access
    Webly Supervised Semantic Segmentation
    • 41
    • Open Access
    Weakly Supervised Semantic Segmentation Based on Co-segmentation
    • 15
    • Open Access
    Annotating Object Instances with a Polygon-RNN
    • 137
    • Open Access
    Bootstrapping the Performance of Webly Supervised Semantic Segmentation
    • 27
    • Open Access
    Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network
    • 50
    • Highly Influenced
    • Open Access
    GraphNet: Learning Image Pseudo Annotations for Weakly-Supervised Semantic Segmentation
    • 5
    • Highly Influenced
    Scribble Supervised Annotation Algorithms of Panoptic Segmentation for Autonomous Driving
    • 1
    • Open Access
    Exploiting Saliency for Object Segmentation from Image Level Labels
    • 96
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES
    Fully Convolutional Networks for Semantic Segmentation
    • 7,146
    • Highly Influential
    • Open Access
    BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
    • 501
    • Open Access
    Learning Deconvolution Network for Semantic Segmentation
    • 1,398
    • Open Access
    Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
    • 370
    • Highly Influential
    • Open Access
    Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
    • 2,422
    • Highly Influential
    • Open Access
    Convolutional feature masking for joint object and stuff segmentation
    • 326
    • Open Access
    Microsoft COCO: Common Objects in Context
    • 10,198
    • Highly Influential
    • Open Access
    What's the Point: Semantic Segmentation with Point Supervision
    • 340
    • Open Access
    Semantic Image Segmentation via Deep Parsing Network
    • 457
    • Highly Influential
    • Open Access
    The Role of Context for Object Detection and Semantic Segmentation in the Wild
    • 619
    • Highly Influential
    • Open Access