14/06/2020

Hyperbolic Image Embeddings

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

Keywords: hyperbolic geometry, few-shot learning, metric learning, image embeddings, person re-identification

Abstract Paper Similar Papers

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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at CVPR 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 10:13 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 16:59 
 0
 0
 0
 0
 2:51 
 0
 0
 0
 0
 10:04 
 0
 0
 0
 0
 10:54 
 0
 0
 0
 0
 17:56 
 0
 0
 0
 0
 2:24 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 14:15 
 0
 0
 0
 0
 19:53 
 0
 0
 0
 0
 10:40 
 0
 0
 0
 0
 12:49 
 0
 0
 0
 0
 7:39 
 0
 0
 0
 0
 1:02 
 0
 0
 1
 1
 4:46 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:20 
 0
 0
 0
 0
 13:51 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 0:44 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 17:18 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 9:02 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 2:51 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 1
 5:11