Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation
It addresses catastrophic forgetting in 3D point cloud segmentation, an incremental improvement for domain-specific applications.
The paper tackles class-incremental learning for 3D point cloud semantic segmentation by proposing a balanced residual distillation learning framework (BRDL) to refine past knowledge and balance learning between old and new classes, achieving a new benchmark with outstanding balance capability in class-biased scenarios.
Class-incremental learning (CIL) enables continuous learning of new classes while mitigating catastrophic forgetting of old ones. For the performance breakthrough of CIL, it is essential yet challenging to effectively refine past knowledge from the base model and balance it with new learning. However, such a challenge has not been considered in current research. This work proposes a balanced residual distillation learning framework (BRDL) to address this gap and advance CIL performance. BRDL introduces a residual distillation strategy to dynamically refine past knowledge by expanding the network structure and a balanced pseudo-label learning strategy to mitigate class bias and balance learning between old and new classes. We apply the proposed BRDL to a challenging 3D point cloud semantic segmentation task where the data is unordered and unstructured. Extensive experimental results demonstrate that BRDL sets a new benchmark with an outstanding balance capability in class-biased scenarios.