# Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network

arXiv: https://arxiv.org/abs/2303.15654 · HTML: https://mlsanity.com/paper/2303.15654/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 28 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Point Convolutional Neural Networks by Extension Operators](https://mlsanity.com/paper/1803.10091/) (2018)
- [Few-Shot Segmentation via Cycle-Consistent Transformer](https://mlsanity.com/paper/2106.02320/) (2021)
- [DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing](https://mlsanity.com/paper/1909.03669/) (2019)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/1909.10469/) (2019)
- [JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds](https://mlsanity.com/paper/2007.06888/) (2020)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification](https://mlsanity.com/paper/1707.06978/) (2017)

## Built on by (most cited first, 16 of 16)

- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Rethinking Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2403.00592/) (2024)
- [No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation](https://mlsanity.com/paper/2404.04050/) (2024)
- [Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model](https://mlsanity.com/paper/2503.16282/) (2025)
- [Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2504.02454/) (2025)
- [Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation](https://mlsanity.com/paper/2311.01989/) (2023)
- [Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation](https://mlsanity.com/paper/2408.13752/) (2024)
- [EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance](https://mlsanity.com/paper/2511.11700/) (2025)
- [SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation](https://mlsanity.com/paper/2603.06572/) (2026)
- [Less is More: Towards Efficient Few-shot 3D Semantic Segmentation via Training-free Networks](https://mlsanity.com/paper/2308.12961/) (2023)
- [Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation](https://mlsanity.com/paper/2401.16051/) (2024)
- [UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration](https://mlsanity.com/paper/2410.22909/) (2024)
- [Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation](https://mlsanity.com/paper/2509.12878/) (2025)
- [TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder](https://mlsanity.com/paper/2512.11926/) (2025)
- [Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration](https://mlsanity.com/paper/2601.01456/) (2026)
- [Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation](https://mlsanity.com/paper/2603.19757/) (2026)

## Abstract (arXiv)

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic segmentation methods usually require large-scale annotated point clouds for training and cannot handle new categories. While a few-shot learning method was proposed recently to address these two problems, it suffers from high computational complexity caused by graph construction and inability to learn fine-grained relationships among points due to the use of pooling operations. In this paper, we further address these problems by developing a new multi-layer transformer network for few-shot point cloud semantic segmentation. In the proposed network, the query point cloud features are aggregated based on the class-specific support features in different scales. Without using pooling operations, our method makes full use of all pixel-level features from the support samples. By better leveraging the support features for few-shot learning, the proposed method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models on the S3DIS dataset and the ScanNet dataset.