TY - JOUR
T1 - Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentation
AU - Wang, Puzuo
AU - Yao, Wei
N1 - Funding Information:
The dataset was provided by the German Society for Photogrammetry, Remote Sensing, and Geoinformation (DGPF). The work described in this paper was substantially supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. PolyU 25211819), and was also supported by a grant from the Hong Kong Polytechnic University (Project No. G-YBZ9).
Publisher Copyright:
© Author(s) 2021.
PY - 2021/6/17
Y1 - 2021/6/17
N2 - Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus, obtaining accurate results with limited ground truth as training data is considerably important. As a simple and effective method, pseudo labels can use information from unlabeled data for training neural networks. In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. An adaptive thresholding strategy was proposed to generate a pseudo-label based on the prediction probability. Pseudo-label learning is an iterative process, and pseudo labels were updated solely on ground-truth weak labels as the model converged to improve the training efficiency. Experiments using the ISPRS 3D sematic labeling benchmark dataset indicated that our proposed method achieved an equally competitive result compared to that using a full supervision scheme with only up to 2‰ of labeled points from the original training set, with an overall accuracy of 83.7% and an average F1 score of 70.2%.
AB - Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus, obtaining accurate results with limited ground truth as training data is considerably important. As a simple and effective method, pseudo labels can use information from unlabeled data for training neural networks. In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. An adaptive thresholding strategy was proposed to generate a pseudo-label based on the prediction probability. Pseudo-label learning is an iterative process, and pseudo labels were updated solely on ground-truth weak labels as the model converged to improve the training efficiency. Experiments using the ISPRS 3D sematic labeling benchmark dataset indicated that our proposed method achieved an equally competitive result compared to that using a full supervision scheme with only up to 2‰ of labeled points from the original training set, with an overall accuracy of 83.7% and an average F1 score of 70.2%.
KW - Airborne Laser Scanning
KW - Point clouds
KW - Pseudo labels
KW - Semantic segmentation
KW - Weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85119686809&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-V-2-2021-43-2021
DO - 10.5194/isprs-annals-V-2-2021-43-2021
M3 - Conference article
SN - 2194-9042
VL - 5
SP - 43
EP - 50
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
IS - 2
ER -