Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks

arXiv:2306.00560v3 Announce Type: replace
Abstract: Computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability distributions. In this context, we investigate the regression-by-classification paradigm which can represent multimodal distributions, without a prior assumption on the number of modes. Through experiments on a specifically designed synthetic dataset, we demonstrate that traditional loss functions lead to poor probability …

abstract applications arxiv classification computer computer vision context cs.lg hinge images multimodal paradigm probability regression safety safety-critical stat.ml study systems tasks type uncertainty values vision