Weakly Supervised Learning Method for Semantic Segmentation of Large-Scale 3D Point Cloud Based on Transformers
Abstract. Nowadays, semantic segmentation results of 3D point cloud have been widely applied in the fields of robotics, autonomous driving, and augmented reality etc. Thanks to the development of relevant deep learning models (such as PointNet), supervised training methods have become hotspot, in which two common limitations exists: inferior feature representation of 3D points and massive annotations. To improve 3D point feature, inspired by the idea of transformer, we employ a so-call LCP network that extracts better feature by investigating attentions between target 3D points and its corresponding local neighbors via local context propagation. Training transformer-based network needs amount of training samples, which itself is a labor-intensive, costly and error-prone work, therefore, this work proposes a weakly supervised framework, in particular, pseudo-labels are estimated based on the feature distances between unlabeled points and prototypes, which are calculated based on labeled data. The extensive experimental results show that, the proposed PL-LCP can yield considerable results (67.6% mIOU for indoor and 67.3% for outdoor) even if only using 1% real labels, and comparing to several state-of-the-art method using all labels, we achieve superior results in mIOU, OA for indoor (65.9%, 89.2%).
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Weakly Supervised Learning Method for Semantic Segmentation of Large-Scale 3D Point Cloud Based on Transformers ; volume:XLVIII-1-2024 ; year:2024 ; pages:887-894 ; extent:8
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLVIII-1-2024 (2024), 887-894 (gesamt 8)
- Urheber
-
Zhang, Zhaoning
Wang, Tengfei
Wang, Xin
Zhan, Zongqian
- DOI
-
10.5194/isprs-archives-XLVIII-1-2024-887-2024
- URN
-
urn:nbn:de:101:1-2405160434579.861096943751
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 02:14 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Zhang, Zhaoning
- Wang, Tengfei
- Wang, Xin
- Zhan, Zongqian
Ähnliche Objekte (12)
Weakly and Semi Supervised Semantic Segmentation of RGB Images
Learning graph structures with transformer for weakly supervised semantic segmentation
Active self-training for weakly supervised 3D scene semantic segmentation
Variability-Aware and Weakly Supervised Learning for Semantic Tissue Segmentation
Learning class-agnostic masks with cross-task refinement for weakly supervised semantic segmentation
Semi-Weakly Supervised Learning for Label-efficient Semantic Segmentation in Expert-driven Domains
On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
WEAKLY SUPERVISED SEMANTIC SEGMENTATION OF SATELLITE IMAGES FOR LAND COVER MAPPING – CHALLENGES AND OPPORTUNITIES
Weakly supervised human skin segmentation using guidance attention mechanisms
CORAL: COde RepresentAtion learning with weakly-supervised transformers for analyzing data analysis
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Pseudo-label noise suppression techniques for semi-supervised semantic segmentation
Weakly and Semi Supervised Semantic Segmentation of RGB Images
Learning graph structures with transformer for weakly supervised semantic segmentation
Active self-training for weakly supervised 3D scene semantic segmentation
Variability-Aware and Weakly Supervised Learning for Semantic Tissue Segmentation
Learning class-agnostic masks with cross-task refinement for weakly supervised semantic segmentation
Semi-Weakly Supervised Learning for Label-efficient Semantic Segmentation in Expert-driven Domains
On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
WEAKLY SUPERVISED SEMANTIC SEGMENTATION OF SATELLITE IMAGES FOR LAND COVER MAPPING – CHALLENGES AND OPPORTUNITIES
Weakly supervised human skin segmentation using guidance attention mechanisms
CORAL: COde RepresentAtion learning with weakly-supervised transformers for analyzing data analysis
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Pseudo-label noise suppression techniques for semi-supervised semantic segmentation
Weakly and Semi Supervised Semantic Segmentation of RGB Images
Learning graph structures with transformer for weakly supervised semantic segmentation
Active self-training for weakly supervised 3D scene semantic segmentation
Variability-Aware and Weakly Supervised Learning for Semantic Tissue Segmentation
Learning class-agnostic masks with cross-task refinement for weakly supervised semantic segmentation
Semi-Weakly Supervised Learning for Label-efficient Semantic Segmentation in Expert-driven Domains
On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
WEAKLY SUPERVISED SEMANTIC SEGMENTATION OF SATELLITE IMAGES FOR LAND COVER MAPPING – CHALLENGES AND OPPORTUNITIES
Weakly supervised human skin segmentation using guidance attention mechanisms
CORAL: COde RepresentAtion learning with weakly-supervised transformers for analyzing data analysis
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation