Hyperbolic Image Embeddings

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

CVPR 2020oral372 citations

Hyperbolic Image Embeddings

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

Abstract

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.

BibTeX

@inproceedings{cvpr2020_hyperbolicimagee,
  title = {Hyperbolic Image Embeddings},
  author = {Valentin Khrulkov and Leyla Mirvakhabova and Evgeniya Ustinova and Ivan Oseledets and Victor Lempitsky},
  booktitle = {CVPR 2020},
  year = {2020}
}