APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
APCoTTA: 用于空中激光雷达点云语义分割的连续测试时间适应
机构 * Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院航空航天信息研究所) ; International Research Center of Big Data for Sustainable Development Goals(可持续发展目标大数据国际研究中心) ; University of Chinese Academy of Sciences(中国科学院大学) ; The Department of Geomatics Engineering, Changsha University of Science and Technology(长沙理工大学测绘工程系) ; The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(武汉大学测绘遥感信息工程国家重点实验室)
专题命中 点云 :point cloud(title,abstract);分类 cs.CV
AI总结 本文提出APCoTTA框架,针对空中激光雷达点云语义分割中的持续领域偏移问题,通过梯度驱动层选择、熵一致性损失和随机参数插值机制提升适应性能,并构建两个基准数据集。
Comments 18 pages,12 figures
Journal ref ISPRS Journal of Photogrammetry and Remote Sensing Volume 237, July 2026, Pages 339-354