The Robust Semantic Segmentation UNCV2023 Challenge Results

TL;DR

This paper presents the results of the ICCV 2023 MUAD uncertainty quantification challenge, showcasing top solutions for robust semantic segmentation in urban environments under natural adversarial conditions.

Contribution

It provides a comprehensive overview of diverse uncertainty quantification techniques applied to semantic segmentation in challenging urban scenarios, highlighting state-of-the-art approaches.

Findings

Top solutions improved robustness in urban semantic segmentation

Diverse uncertainty quantification methods were effective

The challenge highlighted key strategies for handling natural adversarial conditions

Abstract

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.