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.
@article{arxiv.2107.11769,
title = {ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation},
author = {Tsung-Han Wu and Yueh-Cheng Liu and Yu-Kai Huang and Hsin-Ying Lee and Hung-Ting Su and Ping-Chia Huang and Winston H. Hsu},
journal= {arXiv preprint arXiv:2107.11769},
year = {2022}
}
Comments
Accepted by ICCV 2021. The code is available at https://github.com/tsunghan-wu/ReDAL