Hyperbolic Image Embeddings

2019/04/03 by Khrulkov, Valentin, Mirvakhabova, Leyla, Ustinova, Evgeniya +2 · 21 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1904.02239

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.

Cited by

• PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification
• H²em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning
• HyperST: Hierarchical Hyperbolic Learning for Spatial Transcriptomics Prediction
• Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
• LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension
• Climbing the label tree: Hierarchy-preserving contrastive learning for medical imaging
• More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
• HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
• HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
• PHyCLIP: ℓ₁-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
• Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings
• Combined Hyperbolic and Euclidean Soft Triple Loss Beyond the Single Space Deep Metric Learning
• HyperHELM: Hyperbolic Hierarchy Encoding for mRNA Language Modeling
• Talk in Pieces, See in Whole: Disentangling and Hierarchical Aggregating Representations for Language-based Object Detection
• Curvature Learning for Generalization of Hyperbolic Neural Networks
• Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
• Hyperbolic Multimodal Representation Learning for Biological Taxonomies
• Learning Protein-Ligand Binding in Hyperbolic Space
• HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detection
• Cholesky decomposition for symmetric matrices, Riemannian geometry, and random matrices
• Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion

Related

• Hyperbolic Deep Learning in Computer Vision: A Survey
• Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin
• Hyperbolic Geometry in Computer Vision: A Survey
• HVT: A Comprehensive Vision Framework for Learning in Non-Euclidean Space
• Hyperbolic Image Segmentation