Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation
This work addresses the challenge of segmenting unseen categories in point clouds with minimal annotated data, offering an incremental improvement over existing prototype-based methods.
The paper tackles the problem of object variation in few-shot point cloud segmentation by introducing dynamic prototype adaptation (DPA), which learns task-specific prototypes for each query, resulting in significant performance gains of 7.43% and 6.39% on S3DIS and ScanNet benchmarks under 2-way 1-shot settings.
Few-shot point cloud segmentation seeks to generate per-point masks for previously unseen categories, using only a minimal set of annotated point clouds as reference. Existing prototype-based methods rely on support prototypes to guide the segmentation of query point clouds, but they encounter challenges when significant object variations exist between the support prototypes and query features. In this work, we present dynamic prototype adaptation (DPA), which explicitly learns task-specific prototypes for each query point cloud to tackle the object variation problem. DPA achieves the adaptation through prototype rectification, aligning vanilla prototypes from support with the query feature distribution, and prototype-to-query attention, extracting task-specific context from query point clouds. Furthermore, we introduce a prototype distillation regularization term, enabling knowledge transfer between early-stage prototypes and their deeper counterparts during adaption. By iteratively applying these adaptations, we generate task-specific prototypes for accurate mask predictions on query point clouds. Extensive experiments on two popular benchmarks show that DPA surpasses state-of-the-art methods by a significant margin, e.g., 7.43\% and 6.39\% under the 2-way 1-shot setting on S3DIS and ScanNet, respectively. Code is available at https://github.com/jliu4ai/DPA.