Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. While the Contrastive Vision-Language Pre-Training (CLIP) model has been effective in addressing 2D few/zero-shot learning tasks, its direct application to 3D FSCIL faces limitations. These limitations arise from feature space misalignment and significant noise in real-world scanned 3D data. To address these challenges, we introduce two novel components: the Redundant Feature Eliminator (RFE) and the Spatial Noise Compensator (SNC). RFE aligns the feature spaces of input point clouds and their embeddings by performing a unique dimensionality reduction on the feature space of pre-trained models (PTMs), effectively eliminating redundant information without compromising semantic integrity. On the other hand, SNC is a graph-based 3D model designed to capture robust geometric information within point clouds, thereby augmenting the knowledge lost due to projection, particularly when processing real-world scanned data. Considering the imbalance in existing 3D datasets, we also propose new evaluation metrics that offer a more nuanced assessment of a 3D FSCIL model. Traditional accuracy metrics are proved to be biased; thus, our metrics focus on the model's proficiency in learning new classes while maintaining the balance between old and new classes. Experimental results on both established 3D FSCIL benchmarks and our dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods.

翻译：小样本类增量学习（FSCIL）旨在缓解模型在有限数据上增量训练时的灾难性遗忘问题。尽管对比视觉-语言预训练（CLIP）模型在解决二维小/零样本学习任务中效果显著，但其直接应用于三维FSCIL却存在局限性。这些局限性源于特征空间的不对齐以及真实世界扫描三维数据中的显著噪声。为应对这些挑战，我们引入了两个新模块：冗余特征消除器（RFE）和空间噪声补偿器（SNC）。RFE通过对预训练模型（PTM）的特征空间进行独特降维，对齐输入点云及其嵌入的特征空间，在不损害语义完整性的前提下有效消除冗余信息。另一方面，SNC是一种基于图的三维模型，旨在捕获点云中的鲁棒几何信息，从而增强因投影（尤其是在处理真实扫描数据时）而丢失的知识。考虑到现有三维数据集的不平衡性，我们还提出了新的评估指标，以对三维FSCIL模型进行更细致的评估。传统的准确率指标已被证明存在偏差；因此，我们的指标聚焦于模型学习新类的能力，同时保持新旧类之间的平衡。在已建立的三维FSCIL基准数据集及我们自己的数据集上的实验结果表明，我们的方法显著优于现有最先进方法。