Kristian Schwethelm — accepted AI-conference papers

2025

Laplace Sample Information: Data Informativeness Through a Bayesian Lens

Johannes Kaiser, Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis

ICLR 2025poster

Accurately estimating the informativeness of individual samples in a dataset is an important objective in deep learning, as it can guide sample selection, which can improve model efficiency and accuracy by removing redundant or potentially harmful samples. We propose $\text{\textit{Laplace Sample I…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

Ahmad Bdeir, Kristian Schwethelm, Niels Landwehr

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…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗