Hyperbolic Deep Learning in Computer Vision: A Survey

TL;DR

This survey reviews the emerging use of hyperbolic space in computer vision, highlighting its advantages for hierarchical data, robustness, and limited sample learning, and discusses current research themes and open questions.

Contribution

It provides a comprehensive categorization and overview of hyperbolic learning methods in computer vision, including research themes, challenges, and future directions.

Findings

Hyperbolic learning effectively embeds hierarchical structures.

It improves learning from limited data and quantifies uncertainty.

The survey identifies key research themes and open problems.

Abstract

Deep representation learning is a ubiquitous part of modern computer vision. While Euclidean space has been the de facto standard manifold for learning visual representations, hyperbolic space has recently gained rapid traction for learning in computer vision. Specifically, hyperbolic learning has shown a strong potential to embed hierarchical structures, learn from limited samples, quantify uncertainty, add robustness, limit error severity, and more. In this paper, we provide a categorization and in-depth overview of current literature on hyperbolic learning for computer vision. We research both supervised and unsupervised literature and identify three main research themes in each direction. We outline how hyperbolic learning is performed in all themes and discuss the main research problems that benefit from current advances in hyperbolic learning for computer vision. Moreover, we provide a high-level intuition behind hyperbolic geometry and outline open research questions to further advance research in this direction.