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.

通过引入 Redundant Feature Eliminator (RFE) 和 Spatial Noise Compensator (SNC) 两个新颖组件，实现了在有限数据上进行递增训练时对灾难性遗忘问题的减轻。实验结果表明，该方法在现有 3D FSCIL 基准和我们的数据集上明显优于现有的最先进方法。