OPTIMUS-Prime：深度视觉模型的最小且充分的概念解释
OPTIMUS-Prime: Minimal and Sufficient Concept Explanations for Deep Vision Models
AI总结：
提出OPTIMUS框架，基于主蕴含项理论生成视觉热图解释，满足充分性和最小性，提供形式化保证。
摘要：
自动化决策中日益增长的透明度需求已将可解释人工智能（XAI）推向机器学习研究的前沿。然而，在计算机视觉中，现有的解释方法通常优先考虑最终用户的可访问性，而牺牲了形式化保证，在实用性和理论严谨性之间留下了关键差距。在本文中，我们通过引入OPTIMUS（一种用于深度分类模型的基于概念的可视化解释的新框架）来弥补这一差距。OPTIMUS解释采用视觉热图的形式，不仅对最终用户保持可解释性，而且基于成熟的主蕴含项理论，提供了现有基于显著性方法所缺乏的形式化保证。具体来说，OPTIMUS解释满足两个理想性质：充分性，确保被强调的概念可证明地保证分类器的预测；以及最小性，确保这些概念的严格子集不再保留此保证。这两个性质共同产生了逻辑上紧凑且视觉上连贯的解释。我们在视觉分类基准上验证了我们的方法，证明OPTIMUS热图自然且忠实地呈现了模型预测背后的决策相关概念。
英文摘要：
The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research. In computer vision, however, existing explanation methods often prioritize end-user accessibility at the expense of formal guarantees, leaving a critical gap between practical utility and theoretical rigor. In this paper, we address this gap by introducing OPTIMUS, a novel framework for generating concept-based visual explanations for deep classification models. OPTIMUS explanations take the form of visual heatmaps that not only remain interpretable to end users, but are grounded in the well-established theory of prime implicants, providing formal guarantees that have been largely absent from existing saliency-based methods. Specifically, OPTIMUS explanations satisfy two desirable properties: sufficiency, ensuring that the highlighted concepts provably guarantee the classifier's prediction, and minimality, ensuring that no strict subset of those concepts retains this guarantee. Together, these properties yield explanations that are both logically tight and visually coherent. We validate our approach on a visual classification benchmark, demonstrating that OPTIMUS heatmaps naturally and faithfully surface the decision-relevant concepts underlying model predictions.
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。
