Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiong, Ziliang, Jonnarth, Arvi, Eldesokey, Abdelrahman, Johnander, Joakim, Wandt, Bastian, Forssen, Per-Erik
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913398716891136
author Xiong, Ziliang
Jonnarth, Arvi
Eldesokey, Abdelrahman
Johnander, Joakim
Wandt, Bastian
Forssen, Per-Erik
author_facet Xiong, Ziliang
Jonnarth, Arvi
Eldesokey, Abdelrahman
Johnander, Joakim
Wandt, Bastian
Forssen, Per-Erik
contents 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 distribution estimates and severe overconfidence, in the absence of full ground truth distributions. In order to alleviate these issues, we propose hinge-Wasserstein -- a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training. This enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available. In extensive experiments, we show that the proposed loss leads to substantially better uncertainty estimation on two challenging computer vision tasks: horizon line detection and stereo disparity estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2306_00560
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks
Xiong, Ziliang
Jonnarth, Arvi
Eldesokey, Abdelrahman
Johnander, Joakim
Wandt, Bastian
Forssen, Per-Erik
Machine Learning
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 distribution estimates and severe overconfidence, in the absence of full ground truth distributions. In order to alleviate these issues, we propose hinge-Wasserstein -- a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training. This enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available. In extensive experiments, we show that the proposed loss leads to substantially better uncertainty estimation on two challenging computer vision tasks: horizon line detection and stereo disparity estimation.
title Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks
topic Machine Learning
url https://arxiv.org/abs/2306.00560