ML Anthology

Interactive Image Segmentation via Backpropagating Refinement Scheme

Won-Dong Jang, Chang-Su Kim
CVPR 2019
doi:10.1109/CVPR.2019.00544 /cvpr/2019/jang2019cvpr-interactive/

Abstract

An interactive image segmentation algorithm, which accepts user-annotations about a target object and the background, is proposed in this work. We convert user-annotations into interaction maps by measuring distances of each pixel to the annotated locations. Then, we perform the forward pass in a convolutional neural network, which outputs an initial segmentation map. However, the user-annotated locations can be mislabeled in the initial result. Therefore, we develop the backpropagating refinement scheme (BRS), which corrects the mislabeled pixels. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithms on four challenging datasets. Furthermore, we demonstrate the generality and applicability of BRS in other computer vision tasks, by transforming existing convolutional neural networks into user-interactive ones.

PDF CVPR Semantic Scholar

Cite

Text

Jang and Kim. "Interactive Image Segmentation via Backpropagating Refinement Scheme." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00544

Markdown

[Jang and Kim. "Interactive Image Segmentation via Backpropagating Refinement Scheme." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/jang2019cvpr-interactive/) doi:10.1109/CVPR.2019.00544

BibTeX

@inproceedings{jang2019cvpr-interactive,
  title     = {{Interactive Image Segmentation via Backpropagating Refinement Scheme}},
  author    = {Jang, Won-Dong and Kim, Chang-Su},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00544},
  url       = {https://mlanthology.org/cvpr/2019/jang2019cvpr-interactive/}
}