White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentation
By: Jiyun Im , SuBeen Lee , Miso Lee and more
Potential Business Impact:
Teaches computers to understand 3D shapes from few examples.
Few-Shot 3D Point Cloud Segmentation (FS-PCS) aims to predict per-point labels for an unlabeled point cloud, given only a few labeled examples. To extract discriminative representations from the limited support set, existing methods have constructed prototypes using conventional algorithms such as farthest point sampling. However, we point out that its initial randomness significantly affects FS-PCS performance and that the prototype generation process remains underexplored despite its prevalence. This motivates us to investigate an advanced prototype generation method based on attention mechanism. Despite its potential, we found that vanilla module suffers from the distributional gap between learnable prototypical tokens and support features. To overcome this, we propose White Aggregation and Restoration Module (WARM), which resolves the misalignment by sandwiching cross-attention between whitening and coloring transformations. Specifically, whitening aligns the support features to prototypical tokens before attention process, and subsequently coloring restores the original distribution to the attended tokens. This simple yet effective design enables robust attention, thereby generating representative prototypes by capturing the semantic relationships among support features. Our method achieves state-of-the-art performance with a significant margin on multiple FS-PCS benchmarks, demonstrating its effectiveness through extensive experiments.
Similar Papers
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
CV and Pattern Recognition
Helps computers understand pictures with less examples.
RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
CV and Pattern Recognition
Fills in missing parts of 3D scenes faster.
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation
CV and Pattern Recognition
Makes robots see clearly in bad weather.