7 papers
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu +1
Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.…
Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data
Arsalaan Ahmad, Oktay Karakus, Paul L. Rosin
Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic inputs whose contributions rema…
The Sim-to-Real Gap in MRS Quantification: A Systematic Deep Learning Validation for GABA
Zien Ma, S. M. Shermer, Oktay KarakuÅ +1
Magnetic resonance spectroscopy (MRS) is used to quantify metabolites in vivo and estimate biomarkers for conditions ranging from neurological disorders to cancers. Quantifying low…
A Classification-Aware Super-Resolution Framework for Ship Targets in SAR Imagery
Ch Muhammad Awais, Marco Reggiannini, Davide Moroni +1
High-resolution imagery plays a critical role in improving the performance of visual recognition tasks such as classification, detection, and segmentation. In many domains, includi…
What If They Took the Shot? A Hierarchical Bayesian Framework for Counterfactual Expected Goals
Mikayil Mahmudlu, Oktay KarakuÅ, Hasan ArkadaÅ
This study develops a hierarchical Bayesian framework that integrates expert domain knowledge to quantify player-specific effects in expected goals (xG) estimation, addressing a li…
Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference
Benjamin Wiriyapong, Oktay KarakuÅ, Kirill Sidorov
Normalising-flow variational inference (VI) can approximate complex posteriors, yet single-flow models often behave inconsistently across qualitatively different distributions. We…