Hyperbolic Image Segmentation

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Atigh, Mina Ghadimi, Schoep, Julian, Acar, Erman, Van Noord, Nanne, Mettes, Pascal
Format: Conference Proceeding
Language:English
Subjects:
grouping and shape analysis
Image segmentation
Machine learning
Manifolds
Pattern recognition
Segmentation
Semantics
Task analysis
Uncertainty
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!