Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
This addresses the challenge of catastrophic forgetting in LiDAR semantic segmentation for autonomous driving applications, representing an incremental advancement by applying existing continual learning methods to a new data modality.
The paper tackles the problem of class-incremental continual learning for LiDAR point cloud semantic segmentation, adapting strategies like coarse-to-fine learning and achieving results comparable to state-of-the-art continual learning and offline learning on the SemanticKITTI dataset.
During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and self-inpainting. However, the application of continual learning paradigms to point clouds is still unexplored and investigation is required, especially using architectures that capture the sparsity and uneven distribution of LiDAR data. The current paper analyzes the problem of class incremental learning applied to point cloud semantic segmentation, comparing approaches and state-of-the-art architectures. To the best of our knowledge, this is the first example of class-incremental continual learning for LiDAR point cloud semantic segmentation. Different CL strategies were adapted to LiDAR point clouds and tested, tackling both classic fine-tuning scenarios and the Coarse-to-Fine learning paradigm. The framework has been evaluated through two different architectures on SemanticKITTI, obtaining results in line with state-of-the-art CL strategies and standard offline learning.