Weakly Supervised Pseudo-Label Assisted Learning for Als Point Cloud Semantic Segmentation

Abstract

Abstract. 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%.

A survey on weakly supervised 3D point cloud semantic segmentation

“…Finally, the regularisation strategy can well constrain the network training. Wang and Yao [29] developed a two‐stage KPConv‐based network. The first stage consists of training an initial model with known sparse label information and generating the first pseudo labels using this model; the second stage combines known labels and pseudo labels training to get a hybrid model and updates the pseudo labels as the model converges.…”

Exploring Label Initialization for Weakly Supervised Als Point Cloud Semantic Segmentation

“…In Hu et al (2021), a semantic query network was proposed to share sparse weak-label information in the spatial domain by interpolating features from neighboring points. Wang and Yao (2021b) proposed a pseudo-label-assisted approach for point-cloud semantic segmentation using limited annotations. This was enhanced in Wang and Yao (2021a), in which a plug-and-play weakly supervised framework was introduced, comprising entropy regularization, an ensemble prediction constraint, and online pseudo-labeling.…”