Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training
This addresses the challenge of incremental learning in 3D point clouds for applications like robotics and autonomous driving, offering a novel pre-training approach to improve performance without relying on exemplars.
The paper tackles the problem of catastrophic forgetting in class-incremental learning for 3D point clouds by proposing a zero-collection-cost basic shape dataset for pre-training, which helps models gain extensive 3D geometry knowledge and outperforms baseline methods by a large margin in both exemplar-free and exemplar-based settings.
Existing class-incremental learning methods in 3D point clouds rely on exemplars (samples of former classes) to resist the catastrophic forgetting of models, and exemplar-free settings will greatly degrade the performance. For exemplar-free incremental learning, the pre-trained model methods have achieved state-of-the-art results in 2D domains. However, these methods cannot be migrated to the 3D domains due to the limited pre-training datasets and insufficient focus on fine-grained geometric details. This paper breaks through these limitations, proposing a basic shape dataset with zero collection cost for model pre-training. It helps a model obtain extensive knowledge of 3D geometries. Based on this, we propose a framework embedded with 3D geometry knowledge for incremental learning in point clouds, compatible with exemplar-free (-based) settings. In the incremental stage, the geometry knowledge is extended to represent objects in point clouds. The class prototype is calculated by regularizing the data representation with the same category and is kept adjusting in the learning process. It helps the model remember the shape features of different categories. Experiments show that our method outperforms other baseline methods by a large margin on various benchmark datasets, considering both exemplar-free (-based) settings.