Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods typically employ single-stage encoder-decoder architectures where segmentation masks and class labels are tightly coupled, leading to interference between old and new class learning and suboptimal retention-plasticity balance. We introduce DecoupleCSS, a novel two-stage framework for CSS. By decoupling class-aware detection from class-agnostic segmentation, DecoupleCSS enables more effective continual learning, preserving past knowledge while learning new classes. The first stage leverages pre-trained text and image encoders, adapted using LoRA, to encode class-specific information and generate location-aware prompts. In the second stage, the Segment Anything Model (SAM) is employed to produce precise segmentation masks, ensuring that segmentation knowledge is shared across both new and previous classes. This approach improves the balance between retention and adaptability in CSS, achieving state-of-the-art performance across a variety of challenging tasks. Our code is publicly available at: https://github.com/euyis1019/Decoupling-Continual-Semantic-Segmentation.

翻译：持续语义分割（CSS）要求在学习新类别的同时不遗忘先前获得的知识，以解决密集预测任务中灾难性遗忘这一根本性挑战。然而，现有的CSS方法通常采用单阶段编码器-解码器架构，其中分割掩码与类别标签紧密耦合，导致新旧类别学习之间的相互干扰以及次优的保留-可塑性平衡。我们提出了DecoupleCSS，一种新颖的两阶段CSS框架。通过将类别感知检测与类别无关分割解耦，DecoupleCSS实现了更有效的持续学习，在习得新类别的同时保留过去的知识。第一阶段利用预训练的文本和图像编码器（通过LoRA进行适配）来编码类别特定信息并生成位置感知提示。在第二阶段，采用Segment Anything Model（SAM）来生成精确的分割掩码，确保分割知识在新类别与先前类别之间共享。该方法改善了CSS中保留能力与适应能力之间的平衡，在各种具有挑战性的任务上实现了最先进的性能。我们的代码公开于：https://github.com/euyis1019/Decoupling-Continual-Semantic-Segmentation。