Hyperbolic Image Embeddings

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.

Stats

• citations243
• S2 citations—
• github stars0
• HF likes0
• heat score17.91
• arxiv keykhrulkov2019hyperbolic

Related papers

• Hierloc: Hyperbolic Entity Embeddings For Hierarchical Visual Geolocation (2026)0.00
• Hyp-uml: Hyperbolic Image Retrieval With Uncertainty-aware Metric Learning (2023)0.00
• Explicit Formulae To Interchangeably Use Hyperplanes And Hyperballs Using Inversive Geometry (2024)0.00
• Learning Inward Scaled Hypersphere Embedding: Exploring Projections In Higher Dimensions (2018)0.00
• Hyperbolic Image-text Representations (2023)4.61
• ARGENT: Adaptive Hierarchical Image-text Representations (2026)0.00
• Hypevpr: Exploring Hyperbolic Space For Perspective To Equirectangular Visual Place Recognition (2025)0.00
• Predicting Visual Overlap Of Images Through Interpretable Non-metric Box Embeddings (2020)8.82