残差SODAP：基于结构知识保留的残差自组织领域自适应提示法用于持续学习
Residual SODAP: Residual Self-Organizing Domain-Adaptive Prompting with Structural Knowledge Preservation for Continual Learning
AI总结：
本文提出残差SODAP，结合提示表示适应与分类器级知识保留，通过α-entmax稀疏提示选择、残差聚合、数据无关蒸馏与伪特征重放等方法，在无任务ID和额外数据存储的三个DIL基准上取得最优AvgACC/AvgF性能。
摘要：
持续学习（CL）面临灾难性遗忘问题，特别是在领域增量学习（DIL）中，由于任务标识不可用且无法存储过去数据，问题更加严重。尽管基于提示的持续学习（PCL）通过冻结骨干网络来适应表示，但提示-only改进往往不足，因为提示选择不优且在域移位下分类器不稳定。我们提出残差SODAP，联合执行基于提示的表示适应和分类器级知识保留。我们的框架结合α-entmax稀疏提示选择与残差聚合、数据无关蒸馏与伪特征重放、基于提示使用量的域移位检测以及不确定性感知的多损失平衡。在无任务ID或额外数据存储的三个DIL基准上，残差SODAP取得最优AvgACC/AvgF性能：0.850/0.047（DR）、0.760/0.031（皮肤癌）和0.995/0.003（CORe50）。
英文摘要：
Continual learning (CL) suffers from catastrophic forgetting, which is exacerbated in domain-incremental learning (DIL) where task identifiers are unavailable and storing past data is infeasible. While prompt-based CL (PCL) adapts representations with a frozen backbone, we observe that prompt-only improvements are often insufficient due to suboptimal prompt selection and classifier-level instability under domain shifts. We propose Residual SODAP, which jointly performs prompt-based representation adaptation and classifier-level knowledge preservation. Our framework combines $α$-entmax sparse prompt selection with residual aggregation, data-free distillation with pseudo-feature replay, prompt-usage--based drift detection, and uncertainty-aware multi-loss balancing. Across three DIL benchmarks without task IDs or extra data storage, Residual SODAP achieves state-of-the-art AvgACC/AvgF of 0.850/0.047 (DR), 0.760/0.031 (Skin Cancer), and 0.995/0.003 (CORe50).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
