BRAVO 语义分割挑战结果于 UNCV2024

Tuan-Hung Vu; Eduardo Valle; Andrei Bursuc; Tommie Kerssies; Daan de Geus; Gijs Dubbelman; Long Qian; Bingke Zhu; Yingying Chen; Ming Tang; Jinqiao Wang; Tomáš Vojíř; Jan Šochman; Jiří Matas; Michael Smith; Frank Ferrie; Shamik Basu; Christos Sakaridis; Luc Van Gool

BRAVO 语义分割挑战结果于 UNCV2024

计算机视觉与模式识别 2024-10-10 v2 人工智能机器学习

作者: Tuan-Hung Vu , Eduardo Valle , Andrei Bursuc , Tommie Kerssies , Daan de Geus , Gijs Dubbelman , Long Qian , Bingke Zhu , Yingying Chen , Ming Tang , Jinqiao Wang , Tomáš Vojíř , Jan Šochman , Jiří Matas , Michael Smith , Frank Ferrie , Shamik Basu , Christos Sakaridis , Luc Van Gool

在 arXiv 上查看 ↗ PDF ↗

摘要

我们提出统一的 BRAVO 挑战，以基准测试语义分割模型在现实扰动和未知超出分布 (OOD) 场景下的可靠性。我们定义两种可靠性类别：(1) 语义可靠性，即反映模型在暴露于各种扰动时的准确性和校准能力；(2) OOD 可靠性，即衡量模型检测训练期未知目标类别的能力。该挑战吸引了来自国际团队的近 100 项提交，代表着著名研究机构。结果揭示了在开发稳健可靠的语义分割模型中，大规模预训练和最小化架构设计的重要性。

关键词

语义分割可靠性超出分布基准挑战模型鲁棒性

引用

@article{arxiv.2409.15107,
  title  = {The BRAVO Semantic Segmentation Challenge Results in UNCV2024},
  author = {Tuan-Hung Vu and Eduardo Valle and Andrei Bursuc and Tommie Kerssies and Daan de Geus and Gijs Dubbelman and Long Qian and Bingke Zhu and Yingying Chen and Ming Tang and Jinqiao Wang and Tomáš Vojíř and Jan Šochman and Jiří Matas and Michael Smith and Frank Ferrie and Shamik Basu and Christos Sakaridis and Luc Van Gool},
  journal= {arXiv preprint arXiv:2409.15107},
  year   = {2024}
}

备注

ECCV 2024 proceeding paper of the BRAVO challenge 2024, see https://benchmarks.elsa-ai.eu/?ch=1&com=introduction Corrected numbers in Tables 1,3,4,5 and 10

BRAVO 语义分割挑战结果于 UNCV2024

摘要

关键词

引用

备注

相关论文