Hyperbolic Image Segmentation
| Autor: | Mina Ghadimi Atigh, Julian Schoep, Erman Acar, Nanne Van Noord, Pascal Mettes |
|---|---|
| Přispěvatelé: | Artificial intelligence, Network Institute, Knowledge Representation and Reasoning |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
grouping and shape analysis Segmentation Computer Vision and Pattern Recognition (cs.CV) Computer Science::Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): [Proceedings], 4443-4452 STARTPAGE=4443;ENDPAGE=4452;TITLE=2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Atigh, M G, Schoep, J, Acar, E, Van Noord, N & Mettes, P 2022, Hyperbolic Image Segmentation . in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : [Proceedings] . Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2022-June, IEEE Computer Society, pp. 4443-4452, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, United States, 19/06/22 . https://doi.org/10.1109/CVPR52688.2022.00441 |
| DOI: | 10.1109/CVPR52688.2022.00441 |
| Popis: | 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. accepted to CVPR 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|