发表机构
Mohamed bin Zayed University of Artificial Intelligence; Alexandria University（穆罕默德·本·扎耶德人工智能大学; 亚历山大大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究异构医学视觉问答持续学习，通过系统评估多种临床目标任务，探究现有CL方法减轻灾难性遗忘能力、对任务排序敏感性及低秩适应参数演变，发现交错不同任务时现有方法难维持稳定性 - 可塑性平衡。
AI 中文摘要
在实际临床环境中部署医学视觉问答（MedVQA）系统，需要模型能适应新临床任务且不忘先前知识。持续学习（CL）为此提供实用框架。尽管医学视觉语言模型进展迅速，但跨异构MedVQA任务训练时CL方法的行为仍未充分探索。本文对MedVQA的CL进行系统评估，涵盖多种临床目标。具体探究现有CL方法减轻灾难性遗忘的能力、对任务排序的敏感性以及低秩适应参数的演变。结果表明，当不同目标和监督格式的任务交错时，现有CL方法难以维持稳定性 - 可塑性平衡。代码和完整实验设置将公开。
英文摘要
Deploying medical visual question answering (MedVQA) systems in real-world clinical settings requires models that adapt to new clinical tasks without forgetting previously acquired knowledge. Continual learning (CL) provides a practical framework for this setting. Despite rapid progress in medical vision-language models, the behavior of CL methods when training these models across heterogeneous MedVQA tasks remains underexplored. This work presents a systematic evaluation of CL for MedVQA across diverse clinical objectives, including classification, multi-label classification, detection, cell counting, and report generation. Specifically, we explore (1) the ability of existing CL methods to mitigate catastrophic forgetting; (2) their sensitivity to task ordering, analyzing how different task sequences influence performance retention and forgetting; and (3) the evolution of low-rank adaptation parameters as new tasks are learned, revealing patterns of weight drift under different CL methods. Our findings suggest that existing CL methods struggle to maintain stability-plasticity balance when tasks with different objectives and supervision formats are interleaved. Code and full experimental setup will be publicly available.
