Generalized Few-Shot 3D Point Cloud Segmentation

Few-Shot 3D Point Cloud Semantic Segmentation (3D-FS) mitigates the issues of insufficient data annotation and emerging new classes in real-world scenarios, but it totally ignores the performance on base classes. In this paper, we address a more practical task named Generalized Few-Shot 3D Point Cloud Semantic Segmentation (3D-GFS), which aims to perform segmentation on both the base classes with adequate samples and the novel classes with few samples simultaneously. Based on the prototypical Base Model for the 3D-GFS task, we propose an Adaptive Support Enrichment module and a Query Aware Representation module to utilize the contextual information of semantic segmentation. The former exploits the essential co-relationship between base and novel classes in support samples while the latter mines the semantic information from individual query samples. Besides, considering the different embedding spaces, we propose a new training strategy to get a better representation of prototypes for further performance improvement. Extensive experiments on S3DIS and ScanNet show that our proposed method outperforms our Base Model and the conventional 3D-FS methods.