# Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2401.16051 · HTML: https://mlsanity.com/paper/2401.16051/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 22 of 22)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics](https://mlsanity.com/paper/1908.06295/) (2019)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/1807.00652/) (2018)
- [Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2303.11203/) (2023)
- [Self-Distillation from the Last Mini-Batch for Consistency Regularization](https://mlsanity.com/paper/2203.16172/) (2022)
- [Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2305.14335/) (2023)
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://mlsanity.com/paper/2208.06671/) (2022)
- [Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network](https://mlsanity.com/paper/2303.15654/) (2023)
- [MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks](https://mlsanity.com/paper/1911.09418/) (2019)
- [Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds](https://mlsanity.com/paper/1907.12046/) (2019)
- [Deformable Filter Convolution for Point Cloud Reasoning](https://mlsanity.com/paper/1907.13079/) (2019)

## Abstract (arXiv)

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.