The Robust Semantic Segmentation UNCV2023 Challenge Results - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

The Robust Semantic Segmentation UNCV2023 Challenge Results

Juan C Sanmiguel
Rui Peng
  • Fonction : Auteur
Xinyi Wang
  • Fonction : Auteur
Jiaxuan Zhao
  • Fonction : Auteur
  • PersonId : 1319593
Tianhao Wang
  • Fonction : Auteur
Junpei Zhang
  • Fonction : Auteur
  • PersonId : 1319594
Zitao Wang
  • Fonction : Auteur
Yuting Yang
  • Fonction : Auteur
  • PersonId : 1124190
Licheng Jiao
Andrea Pilzer
  • Fonction : Auteur
Andrei Bursuc
  • Fonction : Auteur
Arno Solin
  • Fonction : Auteur
Martin Trapp
  • Fonction : Auteur
Rui Li
  • Fonction : Auteur

Résumé

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, especailly within urban environments.
Fichier principal
Vignette du fichier
2309.15478.pdf (5.65 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04321188 , version 1 (04-04-2024)

Identifiants

Citer

Xuanlong Yu, Juan C Sanmiguel, Xiaowen Zhang, Marcos Escudero-Viñolo, Rui Peng, et al.. The Robust Semantic Segmentation UNCV2023 Challenge Results. 2023 IEEE/CVF International Conference on Computer Vision (ICCVW) Workshops, Oct 2023, Paris, France. pp.4620-4630, ⟨10.1109/iccvw60793.2023.00496⟩. ⟨hal-04321188⟩
51 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More