基于点云差异的主动学习，提升多视角分割效率与可解释性
ViewPCL: a point cloud based active learning method for multi-view segmentation
- 利用多视角预测生成的几何信息差异设计新评分
- 在多个数据集上实现更低标注成本下的高精度分割
- 适合需要高效标注和模型可解释性的三维视觉任务
我们提出一种面向多视角语义分割的新型主动学习框架。该框架基于一个新设计的评分机制，衡量从模型预测中提取的额外几何信息在不同视角下生成的点云分布差异。该方法实现了数据高效且可解释的主动学习。源代码已公开于 https://github.com/chilai235/viewpclAL。
原文摘要 · Abstract (English)
We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived from the model's prediction across different views. Our approach results in a data efficient and explainable active learning method. The source code is available at https://github.com/chilai235/viewpclAL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。