The Robust Semantic Segmentation UNCV2023 Challenge Results
This is an incremental report summarizing existing techniques for enhancing semantic segmentation robustness in autonomous driving, primarily benefiting researchers in computer vision.
The paper presents the winning solutions from the MUAD uncertainty quantification challenge at ICCV 2023, which focused on improving semantic segmentation robustness in urban environments under natural adversarial conditions, with results from 19 submitted entries.
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.