Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3410-3417
DOI: 10.1609/aaai.v37i3.25449 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Canyu Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref).
Abstract (Originalsprache)
3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic segmentation methods usually require large-scale annotated point clouds for training and cannot handle new categories. While a few-shot learning method was proposed recently to address these two problems, it suffers from high computational complexity caused by graph construction and inability to learn fine-grained relationships among points due to the use of pooling operations. In this paper, we further address these problems by developing a new multi-layer transformer network for few-shot point cloud semantic segmentation. In the proposed network, the query point cloud features are aggregated based on the class-specific support features in different scales. Without using pooling operations, our method makes full use of all pixel-level features from the support samples. By better leveraging the support features for few-shot learning, the proposed method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models on the S3DIS dataset and the ScanNet dataset. Our code is available at https://github.com/czzhang179/SCAT.
Zitieren
APA
Zhang, C., Wu, Z., Wu, X., Zhao, Z., & Wang, S. (2023). Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3410-3417. https://doi.org/10.1609/aaai.v37i3.25449
Vancouver
Zhang C, Wu Z, Wu X, Zhao Z, Wang S. Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3410-3417. doi:10.1609/aaai.v37i3.25449
BibTeX
@article{Zhang2023,
author = {Zhang, Canyu and Wu, Zhenyao and Wu, Xinyi and Zhao, Ziyu and Wang, Song},
title = {Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {3},
pages = {3410--3417},
doi = {10.1609/aaai.v37i3.25449}
}
EUVIMED