Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
This work addresses uncertainty estimation for dense prediction tasks like camouflaged object detection, offering incremental improvements over existing methods.
The paper tackles the problem of accurately estimating aleatoric and epistemic uncertainty in dense prediction tasks by proposing a new sampling strategy to approximate the oracle model and introducing a consistency loss to avoid trivial solutions. The results demonstrate accurate deterministic outcomes and reliable uncertainty estimation, validated on camouflaged object detection.
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.