The Robust Semantic Segmentation UNCV2023 Challenge Results

doi:10.1109/ICCVW60793.2023.00496

	The Robust Semantic Segmentation UNCV2023 Challenge Results
	Yu, Xuanlong 1,2; Zuo, Yi 3; Wang, Zitao 3; Zhang, Xiaowen 3; Zhao, Jiaxuan 3; Yang, Yuting 3; Jiao, Licheng 3; Peng, Rui 3; Wang, Xinyi 3; Zhang, Junpei 3; Zhang, Kexin 3; Liu, Fang 3; Alcover-Couso, Roberto 4; Sanmiguel, Juan C.4; Escudero-Viñolo, Marcos 4; Tian, Hanlin 5; Matsui, Kenta 5; Wang, Tianhao 6; Adan, Fahmy 5; Gao, Zhitong7 ; He, Xuming7 ; Bouniot, Quentin 8; Moghaddam, Hossein 8; Rai, Shyam Nandan 9; Cermelli, Fabio 9; Masone, Carlo 9; Pilzer, Andrea 10; Ricci, Elisa 11; Bursuc, Andrei 12; Solin, Arno 13; Trapp, Martin 13; Li, Rui 13; Yao, Angela 14; Chen, Wenlong 5; Simpson, Ivor 15; Campbell, Neill D. F.16; Franchi, Gianni 2
	2023
会议录名称	PROCEEDINGS - 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW 2023
页码	4620-4630
DOI	10.1109/ICCVW60793.2023.00496
摘要	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. © 2023 IEEE.
会议名称	2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
会议地点	Paris, France
会议日期	October 2, 2023 - October 6, 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20240415432424
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/349522
专题	信息科学与技术学院_PI研究组_何旭明组信息科学与技术学院_硕士生
通讯作者	Yu, Xuanlong
作者单位	1.Paris-Saclay University, Satie, France 2.Institut Polytechnique de Paris, U2IS, Ensta Paris, France 3.Xidian University, Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, China 4.Autonomous University of Madrid (UAM), VPU-Lab, Spain 5.Imperial College London, United Kingdom 6.The University of Texas, Dallas, United States 7.ShanghaiTech University, China 8.Institut Polytechnique de Paris, Ltci, Télécom Paris, France 9.Politecnico di Torino, Italy 10.Nvidia Ai Technology Center, Italy 11.University of Trento, Italy 12.Valeo.ai, France 13.Aalto University, Finland 14.National University of Singapore, Singapore 15.University of Sussex, United Kingdom 16.University of Bath, United Kingdom
推荐引用方式 GB/T 7714	Yu, Xuanlong,Zuo, Yi,Wang, Zitao,et al. The Robust Semantic Segmentation UNCV2023 Challenge Results[C]:Institute of Electrical and Electronics Engineers Inc.,2023:4620-4630.