无需存储旧数据，融合点云与网格实现稳定3D增量学习
ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
- 递归更新自相关矩阵，持续积累知识
- 点云引导的网格注意力机制提升多模态融合效果
- 适合需要长期学习新3D类别的场景
我们提出一种新型递归融合模型ReFu，用于无示例的3D类别增量学习，即在不遗忘旧类的前提下学习新3D类别。与依赖历史数据存储或仅处理单一模态的方法不同，ReFu无需存储示例，同时利用点云与网格的互补优势。通过递归更新正则化自相关矩阵，持续积累知识；并设计点云引导的网格注意力融合模块，有效学习两模态间的关联。实验表明，该框架在多个数据集上均优于现有方法。
原文摘要 · Abstract (English)
We introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point clouds and meshes for exemplar-free 3D Class-Incremental Learning, where the model learns new 3D classes while retaining knowledge of previously learned ones. Unlike existing methods that either rely on storing historical data to mitigate forgetting or focus on single data modalities, ReFu eliminates the need for exemplar storage while utilizing the complementary strengths of both point clouds and meshes. To achieve this, we introduce a recursive method which continuously accumulates knowledge by updating the regularized auto-correlation matrix. Furthermore, we propose a fusion module, featuring a Pointcloud-guided Mesh Attention Layer that learns correlations between the two modalities. This mechanism effectively integrates point cloud and mesh features, leading to more robust and stable continual learning. Experiments across various datasets demonstrate that our proposed framework outperforms existing methods in 3D class-incremental learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。