Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network

Canyu Zhang, Zhenyao Wu, Xinyi Wu, Ziyu Zhao, Song Wang

Abstract:

3D point cloud semantic segmentation aims to group all
points into different semantic categories, which benefits im-
portant 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 computa-
tional 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 ag-
gregated based on the class-specific support features in dif-
ferent 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