← Search

Ahmad Bdeir

2 accepted papers

2025

Robust Hyperbolic Learning with Curvature-Aware Optimization

NeurIPS 2025poster

Hyperbolic deep learning has become a growing research direction in computer vision due to the unique properties afforded by the alternate embedding space. The negative curvature and exponentially growing distance metric provide a natural framework for capturing hierarchical relationships between da…

Cited by 4SourceScholar
2024

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

ICLR 2024poster

Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces. However, current HNNs in computer vision rely on Euclidean backbo…