54 citations · 75 across the 10 of their papers we have counts for
10 papers
From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models
Alexej Klushyn, Juan Rivero Sesma, Florian Seligmann +3
YOLO-Pose models provide efficient keypoint localization, but do not quantify the associated spatial uncertainty. We introduce a lightweight post-hoc probabilistic extension that a…
Airborne Magnetic Anomaly Navigation with Neural-Network-Augmented Online Calibration
Antonia Hager, Sven Nebendahl, Alexej Klushyn +3
Airborne Magnetic Anomaly Navigation (MagNav) provides a jamming-resistant and robust alternative to satellite navigation but requires the real-time compensation of the aircraft pl…
Latent Matters: Learning Deep State-Space Models
Alexej Klushyn, Richard Kurle, Maximilian Soelch +2
Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower b…
BALI: Learning Neural Networks via Bayesian Layerwise Inference
Richard Kurle, Alexej Klushyn, Ralf Herbrich
We introduce a new method for learning Bayesian neural networks, treating them as a stack of multivariate Bayesian linear regression models. The main idea is to infer the layerwise…
Learning Flat Latent Manifolds with VAEs
Nutan Chen, Alexej Klushyn, Francesco Ferroni +2
Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, w…
Increasing the Generalisation Capacity of Conditional VAEs
Alexej Klushyn, Nutan Chen, Botond Cseke +2
We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost. The framework of conditional var…
Learning Hierarchical Priors in VAEs
Alexej Klushyn, Nutan Chen, Richard Kurle +2
We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution. To incenti…
Fast Approximate Geodesics for Deep Generative Models
Nutan Chen, Francesco Ferroni, Alexej Klushyn +3
The length of the geodesic between two data points along a Riemannian manifold, induced by a deep generative model, yields a principled measure of similarity. Current approaches ar…
Active Learning based on Data Uncertainty and Model Sensitivity
Nutan Chen, Alexej Klushyn, Alexandros Paraschos +2
Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether th…
Metrics for Deep Generative Models
Nutan Chen, Alexej Klushyn, Richard Kurle +3
Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---th…