-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2021_ICCV, author = {Wu, Tsung-Han and Liu, Yueh-Cheng and Huang, Yu-Kai and Lee, Hsin-Ying and Su, Hung-Ting and Huang, Ping-Chia and Hsu, Winston H.}, title = {ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {15510-15519} }
ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation
Abstract
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.
Related Material