PRISM：基于原型与跨模态语义挖掘的可解释图像识别推理框架
PRISM: Prototype-based Reasoning with Inter-modal Semantic Mining for Interpretable Image Recognition
把文本条件归因图与原型激活图对齐，可在无概念标注的情况下把 part prototype 锚定到语义区域，为可解释分类器提供一条可复用的跨模态原型学习与定位约束思路。
原文依据 aligning attribution maps with prototype activation patterns, PRISM implicitly anchors visual part prototypes to semantically meaningful image regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于原型的方法通过建立中间部件级原型来构建可解释分类器，从而增强图像识别的可解释性，并借助局部证据和对原型样例的参照实现透明的决策过程。然而，现有大多数方法通常依赖单模态视觉监督，并将原型约束在视觉嵌入空间内，这从根本上限制了其与语言条件语义表示的对齐。本文提出 PRISM（基于跨模态语义挖掘的原型推理），这是一个可解释图像识别框架，利用自然语言作为辅助模态来引导类别特定部件原型的学习。PRISM 引入一种信息论归因机制，以文本描述为条件提取语义相关的图像区域。通过将归因图与原型激活模式对齐，PRISM 在无需显式概念标注的情况下，隐式地将视觉部件原型锚定到语义有意义的图像区域。为促进更好的定位并减少原型之间的冗余，我们引入空间紧凑性约束，鼓励每个原型关注互不重叠且空间集中的区域。在多个细粒度基准上的实验表明，PRISM 不仅提升了分类性能，还提供了忠实且语义有据的视觉解释。
英文原文摘要 1503 字符
Prototype-based methods enhance interpretability in image recognition by establishing intermediate part-level prototypes to build interpretable classifiers, enabling transparent decision-making through localized evidence and reference to prototypical examples. However, most existing methods typically depend on unimodal visual supervision and constrain prototypes within the visual embedding space, which inherently restricts their alignment with language-conditioned semantic representations. In this paper, we present PRISM (Prototype-based Reasoning with Inter-modal Semantic Mining), a framework for interpretable image recognition that leverages natural language as an auxiliary modality to guide the learning of class-specific part prototypes. PRISM introduces an information-theoretic attribution mechanism to extract semantically relevant image regions conditioned on textual descriptions. By aligning attribution maps with prototype activation patterns, PRISM implicitly anchors visual part prototypes to semantically meaningful image regions without requiring explicit concept annotations. To promote better localization and reduce redundancy among prototypes, we introduce a spatial compactness constraint that encourages each prototype to attend to non-overlapping and spatially concentrated regions. Experiments on multiple fine-grained benchmarks demonstrate that PRISM not only improves classification performance but also provides faithful and semantically grounded visual explanations.