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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 6417 - 6427
Hauptverfasser: Khrulkov, Valentin, Mirvakhabova, Leyla, Ustinova, Evgeniya, Oseledets, Ivan, Lempitsky, Victor
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2020
Schlagworte:
Computer vision
Extraterrestrial measurements
Geometry
Natural language processing
Task analysis
Visualization
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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