Journal
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
Volume -, Issue -, Pages 4443-4452Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00441
Keywords
-
Funding
- Dutch Ministry of Education, Culture and Science [024.004.022]
Ask authors/readers for more resources
This work proposes a tractable formulation of hierarchical pixel-level classification in hyperbolic space as an alternative approach for image segmentation. It enables uncertainty estimation, boundary information, and improved performance in low-dimensional output embeddings.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available