Hyperbolic Image Embeddings

Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 6417 - 6427
Main Authors: Khrulkov, Valentin, Mirvakhabova, Leyla, Ustinova, Evgeniya, Oseledets, Ivan, Lempitsky, Victor
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2020
Subjects:
Computer vision
Extraterrestrial measurements
Geometry
Natural language processing
Task analysis
Visualization
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity). In this work, we demonstrate that in many practical scenarios, hyperbolic embeddings provide a better alternative.
ISSN:1063-6919
DOI:10.1109/CVPR42600.2020.00645