# Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.14255 · HTML: https://mlsanity.com/paper/2012.14255/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [FaceStudio: Put Your Face Everywhere in Seconds](https://mlsanity.com/paper/2312.02663/) (2023)
- [CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence](https://mlsanity.com/paper/2101.01308/) (2021)
- [Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning](https://mlsanity.com/paper/2109.05749/) (2021)
- [Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview](https://mlsanity.com/paper/2211.08352/) (2022)
- [Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention](https://mlsanity.com/paper/2302.10501/) (2023)
- [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data](https://mlsanity.com/paper/2203.00214/) (2022)
- [Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2302.08785/) (2023)
- [TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2408.15657/) (2024)

## Abstract (arXiv)

Point cloud segmentation is a fundamental visual understanding task in 3D vision. A fully supervised point cloud segmentation network often requires a large amount of data with point-wise annotations, which is expensive to obtain. In this work, we present the Compositional Prototype Network that can undertake point cloud segmentation with only a few labeled training data. Inspired by the few-shot learning literature in images, our network directly transfers label information from the limited training data to unlabeled test data for prediction. The network decomposes the representations of complex point cloud data into a set of local regional representations and utilizes them to calculate the compositional prototypes of a visual concept. Our network includes a key Multi-View Comparison Component that exploits the redundant views of the support set. To evaluate the proposed method, we create a new segmentation benchmark dataset, ScanNet-6i, which is built upon ScanNet dataset. Extensive experiments show that our method outperforms baselines with a significant advantage. Moreover, when we use our network to handle the long-tail problem in a fully supervised point cloud segmentation dataset, it can also effectively boost the performance of the few-shot classes.