ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
This addresses the challenge of continual learning for 3D vision tasks, enabling models to learn new classes while retaining old knowledge without exemplar storage, though it is incremental as it builds on existing multi-modal approaches.
The paper tackled the problem of 3D class-incremental learning without storing historical data by integrating point clouds and meshes, resulting in a model that outperforms existing methods in experiments across various datasets.
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.