ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
This work addresses the high cost of manual labeling for 3D scene understanding, offering a practical solution for applications like autonomous driving and robotics.
The paper tackles the problem of reducing annotation burden in point cloud semantic segmentation by proposing ReDAL, a region-based and diversity-aware active learning framework, achieving 90% of fully supervised performance with less than 15% annotations on S3DIS and 5% on SemanticKITTI.
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.