SEA：通过元素级常识视觉问答评估草图抽象效率
SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering
把 VQA 模型当作「元素存在性检测器」来给草图抽象效率打分，这个无参考、元素级的评估范式可以迁移到任何需要衡量「语义保留 vs 视觉简化」的生成任务上（如简笔画生成、图标/logo 生成、示意图生成的质量评估）。
原文依据 SEA leverages a visual question answering model to determine the presence of each element
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论草图是视觉抽象的一种凝练形式，它通过简化而有目的的笔画传达核心概念，同时省略无关细节。尽管草图具有表现力，但量化草图中语义抽象的效率仍然具有挑战性。现有依赖参考图像、低层视觉特征或识别准确率的评估方法无法捕捉抽象性——这一草图的决定性属性。为解决这些局限，我们提出 SEA（草图抽象效率评估指标），这是一种无参考指标，用于评估草图在保持语义可识别性的前提下，以多经济的方式表示类别定义性视觉元素。这些元素按类别从关于草图中通常描绘特征的常识知识中导出。SEA 利用视觉问答模型判定每个元素是否存在，并返回一个定量分数，反映简单视觉表示下的语义保留程度。为支撑该指标，我们提出 CommonSketch，这是首个语义标注草图数据集，包含 300 个类别的 23,100 幅手绘草图，每幅草图配有说明文字和元素级标注。实验表明，SEA 与人类判断高度一致，并能可靠区分不同抽象效率水平；同时 CommonSketch 作为一个基准，为各类视觉语言模型的元素级草图理解提供了系统评估。
英文原文摘要 1481 字符
A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches.To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under simple visual representations.To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.