Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, Bernt Schiele

CVPR 2017

doi:10.1109/CVPR.2017.181 /cvpr/2017/khoreva2017cvpr-simple/

Abstract

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches 95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.

PDF CVPR Semantic Scholar

Cite

Text

Khoreva et al. "Simple Does It: Weakly Supervised Instance and Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.181

Markdown

[Khoreva et al. "Simple Does It: Weakly Supervised Instance and Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/khoreva2017cvpr-simple/) doi:10.1109/CVPR.2017.181

BibTeX

@inproceedings{khoreva2017cvpr-simple,
  title     = {{Simple Does It: Weakly Supervised Instance and Semantic Segmentation}},
  author    = {Khoreva, Anna and Benenson, Rodrigo and Hosang, Jan and Hein, Matthias and Schiele, Bernt},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.181},
  url       = {https://mlanthology.org/cvpr/2017/khoreva2017cvpr-simple/}
}