In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-parameterization mechanism, named representation compensation (RC) module, to decouple the representation learning of both old and new knowledge. The RC module consists of two dynamically evolved branches with one frozen and one trainable. Besides, we design a pooled cube knowledge distillation strategy on both spatial and channel dimensions to further enhance the plasticity and stability of the model. We conduct experiments on two challenging continual semantic segmentation scenarios, continual class segmentation and continual domain segmentation. Without any extra computational overhead and parameters during inference, our method outperforms state-of-the-art performance. The code is available at \url{https://github.com/zhangchbin/RCIL}.

本文研究了连续语义分割问题，提出使用表示补偿（RC）模块结构再参数化机制，以解决网络需要连续整合新类别但避免灾难性遗忘的问题。通过知识蒸馏策略，增强了模型的可塑性和稳定性。在两个有挑战性的实验场景中，无需任何额外的计算负担和参数，模型的性能超过了最先进的性能。

面向持续语义分割的表示补偿网络