ProtoVQA：一种面向可解释细粒度视觉问答的自适应原型框架
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering
AI总结：
ProtoVQA提出统一原型框架，通过学习问题感知原型和空间约束匹配，同时支持VQA回答与证据定位，并引入VLAS评估解释质量，在Visual7W上实现可解释性与准确率的兼顾。
摘要：
视觉问答（VQA）正越来越多地应用于从通用视觉推理到医疗成像和自主系统等安全关键领域的各种场景，在这些场景中，模型不仅必须提供准确的答案，还必须提供人类能够轻松理解和验证的解释。基于原型的建模通过在纯视觉推理任务中将预测锚定在具有语义意义的区域上，已展现出可解释性方面的潜力，但在VQA背景下仍未得到充分探索。我们提出ProtoVQA，这是一个统一的原型框架，它（i）学习以问题为条件的原型作为推理锚点，将答案与具有判别力的图像区域连接起来，（ii）应用空间约束匹配以确保所选证据具有连贯性和语义相关性，以及（iii）通过共享的原型骨干网络同时支持回答任务和证据定位任务。为了评估解释质量，我们提出了视觉-语言对齐分数（VLAS），用于衡量模型关注区域与真实证据之间的对齐程度。在Visual7W上的实验表明，ProtoVQA在保持有竞争力的准确率的同时，能够产生忠实且细粒度的解释，推动了透明且可信的VQA系统的发展。
英文摘要：
Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate answers but also explanations that humans can easily understand and verify. Prototype-based modeling has shown promise for interpretability by grounding predictions in semantically meaningful regions for purely visual reasoning tasks, yet remains underexplored in the context of VQA. We present ProtoVQA, a unified prototypical framework that (i) learns question-aware prototypes that serve as reasoning anchors, connecting answers to discriminative image regions, (ii) applies spatially constrained matching to ensure that the selected evidence is coherent and semantically relevant, and (iii) supports both answering and grounding tasks through a shared prototype backbone. To assess explanation quality, we propose the Visual-Linguistic Alignment Score (VLAS), which measures how well the model's attended regions align with ground-truth evidence. Experiments on Visual7W show that ProtoVQA yields faithful, fine-grained explanations while maintaining competitive accuracy, advancing the development of transparent and trustworthy VQA systems.
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。
