Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale point-by-point manual annotations is still a significant challenge. To reduce the huge annotation burden, we propose a Region-based and Diversity-aware Active Learning (ReDAL), a general framework for many deep learning approaches, aiming to automatically select only informative and diverse sub-scene regions for label acquisition. Observing that only a small portion of annotated regions are sufficient for 3D scene understanding with deep learning, we use softmax entropy, color discontinuity, and structural complexity to measure the information of sub-scene regions. A diversity-aware selection algorithm is also developed to avoid redundant annotations resulting from selecting informative but similar regions in a querying batch. Extensive experiments show that our method highly outperforms previous active learning strategies, and we achieve the performance of 90% fully supervised learning, while less than 15% and 5% annotations are required on S3DIS and SemanticKITTI datasets, respectively. Our code is publicly available at https://github.com/tsunghan-wu/ReDAL.
翻译:尽管在受监督的云层语义部分的深层次学习取得成功,但获得大规模点对点的人工说明仍然是一个重大挑战。为了减轻巨大的批注负担,我们提议采用基于区域和多样性的主动学习(REDAL)这一许多深层次学习方法的总框架,目的是自动选择仅具有信息性和多样性的次层区域来获取标签。我们注意到,只有一小部分附加说明的区域足以通过深层次学习来了解三维场景,我们使用软式麦克斯酶、色彩不连续和结构复杂性来衡量次系统区域的信息。我们还开发了多样性认知选择算法,以避免因在一组查询中选择信息性但相似的区域而产生多余的说明。广泛的实验表明,我们的方法大大优于以往的积极学习战略,我们实现了90%的全面监督学习,而S3DIS和SmantiKITTI数据集则分别需要不到15%和5%的说明。我们的代码在https://github.com/tunghan-wu/REAL上公开提供。