Hyperbolic Image Embeddings

Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, Victor Lempitsky

Research output: Contribution to journalConference articlepeer-review

49 Citations (Scopus)


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.

Original languageEnglish
Article number9156432
Pages (from-to)6417-6427
Number of pages11
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publication statusPublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020


Dive into the research topics of 'Hyperbolic Image Embeddings'. Together they form a unique fingerprint.

Cite this