Uncertainty estimation in Deep Learning for Panoptic segmentation

TL;DR

This paper explores how ensemble-based uncertainty estimation methods like Monte Carlo Dropout can be effectively applied to panoptic segmentation, improving robustness and uncertainty quantification without modifying existing architectures.

Contribution

It demonstrates the applicability of ensemble-based uncertainty estimation in panoptic segmentation, providing improved performance and uncertainty measures without changing existing networks.

Findings

Enhanced uncertainty estimation in panoptic segmentation

Improved robustness on COCO, KITTI-STEP, VIPER datasets

No modifications needed for existing architectures

Abstract

As deep learning-based computer vision algorithms continue to advance the state of the art, their robustness to real-world data continues to be an issue, making it difficult to bring an algorithm from the lab to the real world. Ensemble-based uncertainty estimation approaches such as Monte Carlo Dropout have been successfully used in many applications in an attempt to address this robustness issue. Unfortunately, it is not always clear if such ensemble-based approaches can be applied to a new problem domain. This is the case with panoptic segmentation, where the structure of the problem and architectures designed to solve it means that unlike image classification or even semantic segmentation, the typical solution of using a mean across samples cannot be directly applied. In this paper, we demonstrate how ensemble-based uncertainty estimation approaches such as Monte Carlo Dropout can be used in the panoptic segmentation domain with no changes to an existing network, providing both improved performance and more importantly a better measure of uncertainty for predictions made by the network. Results are demonstrated quantitatively and qualitatively on the COCO, KITTI-STEP and VIPER datasets.