The Robust Semantic Segmentation UNCV2023 Challenge Results
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.
Cite
@article{arxiv.2309.15478,
title = {The Robust Semantic Segmentation UNCV2023 Challenge Results},
author = {Xuanlong Yu and Yi Zuo and Zitao Wang and Xiaowen Zhang and Jiaxuan Zhao and Yuting Yang and Licheng Jiao and Rui Peng and Xinyi Wang and Junpei Zhang and Kexin Zhang and Fang Liu and Roberto Alcover-Couso and Juan C. SanMiguel and Marcos Escudero-Viñolo and Hanlin Tian and Kenta Matsui and Tianhao Wang and Fahmy Adan and Zhitong Gao and Xuming He and Quentin Bouniot and Hossein Moghaddam and Shyam Nandan Rai and Fabio Cermelli and Carlo Masone and Andrea Pilzer and Elisa Ricci and Andrei Bursuc and Arno Solin and Martin Trapp and Rui Li and Angela Yao and Wenlong Chen and Ivor Simpson and Neill D. F. Campbell and Gianni Franchi},
journal= {arXiv preprint arXiv:2309.15478},
year = {2023}
}
Comments
11 pages, 4 figures, accepted at ICCV 2023 UNCV workshop