# Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2603.19788 · HTML: https://mlsanity.com/paper/2603.19788/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [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)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Reducing Overfitting in Deep Networks by Decorrelating Representations](https://mlsanity.com/paper/1511.06068/) (2015)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?](https://mlsanity.com/paper/1810.09102/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/2507.10485/) (2025)
- [Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning](https://mlsanity.com/paper/2303.09483/) (2023)
- [Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2305.14335/) (2023)
- [Prototype-based Incremental Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2012.01415/) (2020)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [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)
- [Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model](https://mlsanity.com/paper/2503.16282/) (2025)
- [Few-shot Class-incremental Learning for 3D Point Cloud Objects](https://mlsanity.com/paper/2205.15225/) (2022)
- [Generalized Few-Shot Point Cloud Segmentation Via Geometric Words](https://mlsanity.com/paper/2309.11222/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation](https://mlsanity.com/paper/2609.12099/) (2026)

## Abstract (arXiv)

Generalized few-shot 3D point cloud segmentation aims to adapt to novel classes from only a few annotations while maintaining strong performance on base classes, but this remains challenging due to the inherent stability-plasticity trade-off: adapting to novel classes can interfere with shared representations and cause base-class forgetting. We present HOP3D, a unified framework that learns hierarchical orthogonal prototypes with an entropy-based few-shot regularizer to enable robust novel-class adaptation without degrading base-class performance. HOP3D introduces hierarchical orthogonalization that decouples base and novel learning at both the gradient and representation levels, effectively mitigating base-novel interference. To further enhance adaptation under sparse supervision, we incorporate an entropy-based regularizer that leverages predictive uncertainty to refine prototype learning and promote balanced predictions. Extensive experiments on ScanNet200 and ScanNet++ demonstrate that HOP3D consistently outperforms state-of-the-art baselines under both 1-shot and 5-shot settings. The code is available at https://fdueblab-hop3d.github.io/.