papers AI Learner
The Github is limit! Click to go to the new site.

Hyperbolic Image Embeddings

2019-04-03
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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.02239

PDF

http://arxiv.org/pdf/1904.02239


Similar Posts

Comments