Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model

TL;DR

This paper introduces a novel ensemble-based conditional latent variable model that improves uncertainty estimation in dense prediction tasks by addressing limitations in existing methods for aleatoric and epistemic uncertainties.

Contribution

It proposes a new sampling strategy for aleatoric uncertainty and a consistency loss to prevent trivial solutions, enhancing uncertainty estimation accuracy.

Findings

Achieves accurate deterministic predictions.

Provides reliable uncertainty estimates.

Validates on camouflaged object detection.

Abstract

Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty. In current aleatoric uncertainty estimation frameworks, it is often neglected that the aleatoric uncertainty is an inherent attribute of the data and can only be correctly estimated with an unbiased oracle model. Since the oracle model is inaccessible in most cases, we propose a new sampling and selection strategy at train time to approximate the oracle model for aleatoric uncertainty estimation. Further, we show a trivial solution in the dual-head based heteroscedastic aleatoric uncertainty estimation framework and introduce a new uncertainty consistency loss to avoid it. For epistemic uncertainty estimation, we argue that the internal variable in a conditional latent variable model is another source of epistemic uncertainty to model the predictive distribution and explore the limited knowledge about the hidden true model. We validate our observation on a dense prediction task, i.e., camouflaged object detection. Our results show that our solution achieves both accurate deterministic results and reliable uncertainty estimation.