ML Anthology

End-to-End Learned Random Walker for Seeded Image Segmentation

Lorenzo Cerrone, Alexander Zeilmann, Fred A. Hamprecht
CVPR 2019
doi:10.1109/CVPR.2019.01284 /cvpr/2019/cerrone2019cvpr-endtoend/

Abstract

We present an end-to-end learned algorithm for seeded segmentation. Our method is based on the Random Walker algorithm, where we predict the edge weights of the un- derlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusiv- ities for a linear diffusion process. After calculating the exact gradient for optimizing these diffusivities, we pro- pose simplifications that sparsely sample the gradient while still maintaining competitive results. The proposed method achieves the currently best results on the seeded CREMI neuron segmentation challenge.

PDF CVPR Semantic Scholar

Cite

Text

Cerrone et al. "End-to-End Learned Random Walker for Seeded Image Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01284

Markdown

[Cerrone et al. "End-to-End Learned Random Walker for Seeded Image Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/cerrone2019cvpr-endtoend/) doi:10.1109/CVPR.2019.01284

BibTeX

@inproceedings{cerrone2019cvpr-endtoend,
  title     = {{End-to-End Learned Random Walker for Seeded Image Segmentation}},
  author    = {Cerrone, Lorenzo and Zeilmann, Alexander and Hamprecht, Fred A.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.01284},
  url       = {https://mlanthology.org/cvpr/2019/cerrone2019cvpr-endtoend/}
}