A new weakly supervised approach for ALS point cloud semantic segmentation

Wang, Puzuo; Yao, Wei

doi:10.48550/arxiv.2110.01462

Cited by 4 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. Because of the flexibility and competitive results achieved using only 1‰ of labels, it was used in this study to explore the effectiveness of weak-label initialization strategies.…”

Section: Weakly Supervised Learningmentioning

confidence: 99%

Exploring Label Initialization for Weakly Supervised Als Point Cloud Semantic Segmentation

Wang

Yao

2022

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Although a number of emerging point-cloud semantic segmentation methods achieve state-of-the-art results, acquiring fully interpreted training data is a time-consuming and labor-intensive task. To reduce the burden of data annotation in training, semiand weakly supervised methods are proposed to address the situation of limited supervisory sources, achieving competitive results compared to full supervision schemes. However, given a fixed budget, the effective annotation of a few points is typically ignored, which is referred to as weak-label initialization in this study. In practice, random selection is typically adopted by default. Because weakly supervised methods largely rely on semantic information supplied by initial weak labels, this studies explores the influence of different weak-label initialization strategies. In addition to random initialization, we propose a feature-constrained framework to guide the selection of initial weak labels. A feature space of point clouds is first constructed by feature extraction and embedding. Then, we develop a density-biased strategy to annotate points by locating highly dense clustered regions, as significant information distinguishing semantic classes is often concentrated in such areas. Our method outperforms random initialization on ISPRS Vaihingen 3D data when only using sparse weak labels, achieving an overall accuracy of 78.06% using 1‰ of labels. However, only a minor increase is observed on the LASDU dataset. Additionally, the results show that initialization with category-wise uniformly distributed weak labels is more effective when incorporated using a weakly supervised method.

show abstract

Section: Weakly Supervised Learningmentioning

confidence: 99%

Exploring Label Initialization for Weakly Supervised Als Point Cloud Semantic Segmentation

Wang

Yao

2022

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…There are some DL-based methods being proposed recently for the weakly supervised point cloud segmentation task [40,27,36,9,60,20,7,12,56,10,51,30]. For example, Wang et al [39] proposed to generate point cloud segmentation labels by back-projecting 2D image annotations to 3D spaces.…”

Section: Weakly Supervised Point Cloud Segmentationmentioning

confidence: 99%

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Wu¹,

Wu²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (Dual Adaptive Transformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.

show abstract

“…To fully exploit unlabelled data, Xu and Lee (2020) introduce three constraints: inexact supervision ensures all categories at a block level are consistent with the pointwise labels in this block, self-supervision keeps the feature consistency when a point cloud is randomly rotated or flipped and a spatial and colour constraint smooths the network outputs. Wang and Yao (2021) 2020) first set up the baseline for weak supervision with scene and subcloud level annotations which are easier to acquire compared to point annotations.…”

Section: Deep Learning On Point Clouds With Fewer Annotation Effortsmentioning

confidence: 99%

“…Semi-supervised learning has also been investigated to alleviate annotation efforts. The idea is to assign semantic labels to a part of the points and models not only learn from the small set of labelled data but also exploit the potentials in the rest of the unlabelled data which take a larger proportion (Deng et al, 2022;Hu et al, 2021;Wang and Yao, 2021;Xu and Lee, 2020). Unsupervised learning is an alternative approach to addressing the problem.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for semantic segmentation of airborne laser scanning point clouds

Lin¹

View full text Add to dashboard Cite

show abstract

A new weakly supervised approach for ALS point cloud semantic segmentation

Cited by 4 publications

References 0 publications

Exploring Label Initialization for Weakly Supervised Als Point Cloud Semantic Segmentation

Exploring Label Initialization for Weakly Supervised Als Point Cloud Semantic Segmentation

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Deep learning for semantic segmentation of airborne laser scanning point clouds

Contact Info

Product

Resources

About