# ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2504.01648 · HTML: https://mlsanity.com/paper/2504.01648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 2 Apr 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [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)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud](https://mlsanity.com/paper/2207.11919/) (2022)
- [Gradient Reweighting: Towards Imbalanced Class-Incremental Learning](https://mlsanity.com/paper/2402.18528/) (2024)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [InCloud: Incremental Learning for Point Cloud Place Recognition](https://mlsanity.com/paper/2203.00807/) (2022)
- [I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting](https://mlsanity.com/paper/2012.09014/) (2020)
- [Few-shot Class-incremental Learning for 3D Point Cloud Objects](https://mlsanity.com/paper/2205.15225/) (2022)
- [Learning to Optimally Segment Point Clouds](https://mlsanity.com/paper/1912.04976/) (2019)
- [LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation](https://mlsanity.com/paper/2103.09160/) (2021)
- [Neural Network Retraining for Model Serving](https://mlsanity.com/paper/2004.14203/) (2020)

## Abstract (arXiv)

3D point cloud semantic segmentation technology has been widely used. However, in real-world scenarios, the environment is evolving. Thus, offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes. Class-incremental learning (CIL) is designed to address the problem of catastrophic forgetting. While point clouds are common, we observe high similarity and unclear boundaries between different classes. Meanwhile, they are known to be imbalanced in class distribution. These lead to issues including misclassification between similar classes and the long-tail problem, which have not been adequately addressed in previous CIL methods. We thus propose ProtoGuard and PROPEL (Progressive Refinement Of PsEudo-Labels). In the base-class training phase, ProtoGuard maintains geometric and semantic prototypes for each class, which are combined into prototype features using an attention mechanism. In the novel-class training phase, PROPEL inherits the base feature extractor and classifier, guiding pseudo-label propagation and updates based on density distribution and semantic similarity. Extensive experiments show that our approach achieves remarkable results on both the S3DIS and ScanNet datasets, improving the mIoU of 3D point cloud segmentation by a maximum of 20.39% under the 5-step CIL scenario on S3DIS.