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)
计算机视觉任务，如图像分类、图像检索和少数镜头学习，目前主要由欧几里得和球面嵌入，以便最终决定类归属或相似程度是使用线性超平面、欧几里得距离或球面测地距离（余弦相似）。在这项工作中，我们证明在许多实际场景中，双曲线嵌入提供了更好的选择。
URL
https://arxiv.org/abs/1904.02239
