提问并记忆：一种用于持续视觉问答的仅问题回放策略
Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering
AI总结：
针对持续视觉问答中的可塑性-稳定性困境，本文提出QUAD，仅回放历史问题并结合注意力一致性蒸馏，在降低存储与隐私风险的同时显著提升性能。
摘要：
视觉问答中的持续学习（VQACL）要求模型在获得新的视觉-语言技能（可塑性）的同时，保留先前学到的知识（稳定性）。VQACL固有的多模态性加剧了这一挑战，因为模型在适应新对象和推理任务时，必须平衡视觉与文本领域的稳定性。现有方法主要为单模态场景设计，往往难以满足这种双重需求。在本文中，我们提出了用于VQACL的QUestion-only replay with Attention Distillation（QUAD，仅问题回放与注意力蒸馏），这是一种仅利用过去任务问题进行正则化的新颖方法。通过消除存储视觉数据的需求，QUAD不仅降低了内存开销，还缓解了隐私问题。我们的方法引入了仅问题回放机制，该机制选择性地复用先前任务的问题，以抵消对当前任务答案空间的过拟合，解决答案集之外的问题。作为补充，我们提出注意力一致性蒸馏，以在跨任务时强制实现模态内和模态间的注意力一致性，保留关键的视觉-语言关联。在VQAv2和NExT-QA上的大量实验表明，QUAD显著优于最先进方法，在持续VQA中取得了稳健性能。代码可在https://github.com/IemProg/QUAD获取。
英文摘要：
Continual Learning in Visual Question Answering (VQACL) requires models to acquire new visual-linguistic skills (plasticity) while preserving previously learned knowledge (stability). The inherent multimodality of VQACL exacerbates this challenge, as models must balance stability across visual and textual domains while adapting to novel objects and reasoning tasks. Existing methods, primarily designed for unimodal settings, often fall short in addressing this dual requirement. In this work, we present QUestion-only replay with Attention Distillation (QUAD), a novel approach for VQACL that leverages only past task questions for regularization. By eliminating the need to store visual data, QUAD not only reduces memory overhead, but also alleviates privacy concerns. Our method introduces a Question-only Replay mechanism that selectively reuses prior task questions to counteract overfitting to the answer space of the current task, addressing the problem out of answer set. Complementing this, we propose Attention Consistency Distillation to enforce both intra-modal and inter-modal attention consistency across tasks, preserving essential visual-linguistic associations. Extensive experiments on VQAv2 and NExT-QA demonstrate that QUAD significantly outperforms state-of-the-art methods, achieving robust performance in continual VQA. Code is available at: https://github.com/IemProg/QUAD.
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。
