# Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection

arXiv: https://arxiv.org/abs/2210.05593 · HTML: https://mlsanity.com/paper/2210.05593/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 59 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [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)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)

## Built on by (most cited first, 14 of 14)

- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Commonsense Prototype for Outdoor Unsupervised 3D Object Detection](https://mlsanity.com/paper/2404.16493/) (2024)
- [Generalized Few-Shot Point Cloud Segmentation Via Geometric Words](https://mlsanity.com/paper/2309.11222/) (2023)
- [Aligning Effective Tokens with Video Anomaly in Large Language Models](https://mlsanity.com/paper/2508.06350/) (2025)
- [Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity](https://mlsanity.com/paper/2409.05466/) (2024)
- [Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes](https://mlsanity.com/paper/2504.18355/) (2025)
- [Few-Shot Learning in Video and 3D Object Detection: A Survey](https://mlsanity.com/paper/2507.17079/) (2025)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [PartCom: Part Composition Learning for 3D Open-Set Recognition](https://mlsanity.com/paper/2211.10880/) (2022)
- [CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection](https://mlsanity.com/paper/2408.17036/) (2024)
- [From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning](https://mlsanity.com/paper/2503.06282/) (2025)
- [CasPoinTr: Point Cloud Completion with Cascaded Networks and Knowledge Distillation](https://mlsanity.com/paper/2509.23375/) (2025)
- [TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder](https://mlsanity.com/paper/2512.11926/) (2025)
- [Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning](https://mlsanity.com/paper/2602.21484/) (2026)

## Abstract (arXiv)

Most existing 3D point cloud object detection approaches heavily rely on large amounts of labeled training data. However, the labeling process is costly and time-consuming. This paper considers few-shot 3D point cloud object detection, where only a few annotated samples of novel classes are needed with abundant samples of base classes. To this end, we propose Prototypical VoteNet to recognize and localize novel instances, which incorporates two new modules: Prototypical Vote Module (PVM) and Prototypical Head Module (PHM). Specifically, as the 3D basic geometric structures can be shared among categories, PVM is designed to leverage class-agnostic geometric prototypes, which are learned from base classes, to refine local features of novel categories.Then PHM is proposed to utilize class prototypes to enhance the global feature of each object, facilitating subsequent object localization and classification, which is trained by the episodic training strategy. To evaluate the model in this new setting, we contribute two new benchmark datasets, FS-ScanNet and FS-SUNRGBD. We conduct extensive experiments to demonstrate the effectiveness of Prototypical VoteNet, and our proposed method shows significant and consistent improvements compared to baselines on two benchmark datasets.