Hyperbolic Image Segmentation

Mina Ghadimi Atigh, Julian Schoep, Erman Acar, Nanne van Noord, Pascal Mettes

CVPR 2022 pp. 4453-4462

doi:10.1109/CVPR52688.2022.00441 /cvpr/2022/atigh2022cvpr-hyperbolic/

Abstract

For image segmentation, the current standard is to perform pixel-level optimization and inference in Euclidean output embedding spaces through linear hyperplanes. In this work, we show that hyperbolic manifolds provide a valuable alternative for image segmentation and propose a tractable formulation of hierarchical pixel-level classification in hyperbolic space. Hyperbolic Image Segmentation opens up new possibilities and practical benefits for segmentation, such as uncertainty estimation and boundary information for free, zero-label generalization, and increased performance in low-dimensional output embeddings.

PDF CVPR Semantic Scholar

Cite

Text

Atigh et al. "Hyperbolic Image Segmentation." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00441

Markdown

[Atigh et al. "Hyperbolic Image Segmentation." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/atigh2022cvpr-hyperbolic/) doi:10.1109/CVPR52688.2022.00441

BibTeX

@inproceedings{atigh2022cvpr-hyperbolic,
  title     = {{Hyperbolic Image Segmentation}},
  author    = {Atigh, Mina Ghadimi and Schoep, Julian and Acar, Erman and van Noord, Nanne and Mettes, Pascal},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2022},
  pages     = {4453-4462},
  doi       = {10.1109/CVPR52688.2022.00441},
  url       = {https://mlanthology.org/cvpr/2022/atigh2022cvpr-hyperbolic/}
}