# Few-shot Class-incremental Learning for 3D Point Cloud Objects arXiv: https://arxiv.org/abs/2205.15225 ยท HTML: https://mlsanity.com/paper/2205.15225/ ## Key facts - Cited by 13 papers in the map (data through 14 Oct 2026). - Builds on 39 of its 52 references that are in the map. - First posted on arXiv 30 May 2022. ## Builds on (most cited first, 30 of 39) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [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) - [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013) - [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015) - [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016) - [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016) - [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018) - [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020) - [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015) - [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017) - [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017) - [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018) - [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018) - [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019) - [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020) - [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018) - [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021) - [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018) - [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019) - [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018) - [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018) - [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019) - [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017) - [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018) - [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020) - [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020) - [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022) - [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021) - [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021) ## Built on by (most cited first, 13 of 13) - [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023) - [Generalized Few-Shot Point Cloud Segmentation Via Geometric Words](https://mlsanity.com/paper/2309.11222/) (2023) - [Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data](https://mlsanity.com/paper/2304.03980/) (2023) - [Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models](https://mlsanity.com/paper/2411.14495/) (2024) - [Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection](https://mlsanity.com/paper/2409.08388/) (2024) - [PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark](https://mlsanity.com/paper/2304.06775/) (2023) - [MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction](https://mlsanity.com/paper/2410.06418/) (2024) - [Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor](https://mlsanity.com/paper/2410.09237/) (2024) - [PartCom: Part Composition Learning for 3D Open-Set Recognition](https://mlsanity.com/paper/2211.10880/) (2022) - [Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation](https://mlsanity.com/paper/2603.19788/) (2026) - [ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning](https://mlsanity.com/paper/2409.12326/) (2024) - [ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation](https://mlsanity.com/paper/2504.01648/) (2025) - [Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning](https://mlsanity.com/paper/2609.04860/) (2026) ## Abstract (arXiv) Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training. Recent efforts address this problem primarily on 2D images. However, due to the advancement of camera technology, 3D point cloud data has become more available than ever, which warrants considering FSCIL on 3D data. This paper addresses FSCIL in the 3D domain. In addition to well-known issues of catastrophic forgetting of past knowledge and overfitting of few-shot data, 3D FSCIL can bring newer challenges. For example, base classes may contain many synthetic instances in a realistic scenario. In contrast, only a few real-scanned samples (from RGBD sensors) of novel classes are available in incremental steps. Due to the data variation from synthetic to real, FSCIL endures additional challenges, degrading performance in later incremental steps. We attempt to solve this problem using Microshapes (orthogonal basis vectors) by describing any 3D objects using a pre-defined set of rules. It supports incremental training with few-shot examples minimizing synthetic to real data variation. We propose new test protocols for 3D FSCIL using popular synthetic datasets (ModelNet and ShapeNet) and 3D real-scanned datasets (ScanObjectNN and CO3D). By comparing state-of-the-art methods, we establish the effectiveness of our approach in the 3D domain.