ML Anthology

CellTypeGraph: A New Geometric Computer Vision Benchmark

Lorenzo Cerrone, Athul Vijayan, Tejasvinee Mody, Kay Schneitz, Fred A. Hamprecht
CVPR 2022 pp. 20897-20907
doi:10.1109/CVPR52688.2022.02023 /cvpr/2022/cerrone2022cvpr-celltypegraph/

Abstract

Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology. We here abstract the problem into a new benchmark for node classification in a geo-referenced graph. Solving it requires learning the spatial layout of the organ including symmetries. To allow the convenient testing of new geometrical learning methods, the benchmark of Arabidopsis thaliana ovules is made available as a PyTorch data loader, along with a large number of precomputed features. Finally, we benchmark eight recent graph neural network architectures, finding that DeeperGCN currently works best on this problem.

PDF CVPR Semantic Scholar

Cite

Text

Cerrone et al. "CellTypeGraph: A New Geometric Computer Vision Benchmark." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.02023

Markdown

[Cerrone et al. "CellTypeGraph: A New Geometric Computer Vision Benchmark." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/cerrone2022cvpr-celltypegraph/) doi:10.1109/CVPR52688.2022.02023

BibTeX

@inproceedings{cerrone2022cvpr-celltypegraph,
  title     = {{CellTypeGraph: A New Geometric Computer Vision Benchmark}},
  author    = {Cerrone, Lorenzo and Vijayan, Athul and Mody, Tejasvinee and Schneitz, Kay and Hamprecht, Fred A.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2022},
  pages     = {20897-20907},
  doi       = {10.1109/CVPR52688.2022.02023},
  url       = {https://mlanthology.org/cvpr/2022/cerrone2022cvpr-celltypegraph/}
}