End-to-end learned random walker for seeded image segmentation
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 underlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusivities for a linear dif...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
22 May 2019
|
| In: |
Arxiv
Year: 2019, Pages: 1-11 |
| DOI: | 10.48550/arXiv.1905.09045 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.1905.09045 Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1905.09045 
|
| Author Notes: | Lorenzo Cerrone, Alexander Zeilmann, Fred A. Hamprecht |
| Summary: | 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 underlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusivities for a linear diffusion process. Besides calculating the exact gradient for optimizing these diffusivities, we also propose simplifications that sparsely sample the gradient and still yield competitive results. The proposed method achieves the currently best results on a seeded version of the CREMI neuron segmentation challenge. |
|---|---|
| Item Description: | Gesehen am 13.07.2022 |
| Physical Description: | Online Resource |
| DOI: | 10.48550/arXiv.1905.09045 |