Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation

• Main Authors: Lai, Lvlong, Chen, Jian, Zhang, Chi, Zhang, Zehong, Lin, Guosheng, Wu, Qingyao
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2022
• 主題: Engineering::Computer science and engineering; Few-Shot; Point Cloud
• 在線閱讀: https://hdl.handle.net/10356/163370

Few-shot point cloud semantic segmentation learns to segment novel classes with scarce labeled samples. Within an episode, a novel target class is defined by a few support samples with corresponding binary masks, where only the points of this class are labeled as foreground and others are regarded a...