Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
This work addresses the problem of few-shot semantic segmentation for 3D point cloud scenes, which is incremental as it builds on existing metric learning frameworks with a novel feature globalization method.
The paper tackles the challenge of few-shot segmentation of 3D point clouds by proposing a bidirectional feature globalization (BFG) approach that embeds global perception into local features, resulting in significant performance improvements over state-of-the-art methods on S3DIS and ScanNet datasets.
Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.