提出可校准的分层图像分类模型，兼顾全局与局部解释性。
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
- 采用对比解释法提升全局可解释性，支持分层推理路径。
- 点预测准确率达99%，与非可解释模型相当，且保持高置信度。
- 内置可解释的合流预测机制，适合医疗等高风险场景使用。
全局可解释模型在安全关键领域中是可信AI的有前景方向。除了全局解释外，详细的局部解释对辅助人类专家决策至关重要。本文提出校准分层质量预测模型（CHiQPM），首次实现全面的全局与局部可解释性，推动人机协同。该模型通过对比方式解释多数类别，提供类人推理风格的分层解释，并可沿层级路径构建内置的可解释合流预测（CP）方法。综合评估表明，CHiQPM在点预测上达到当前最优性能，准确率保持99%，与非可解释模型相当，证明在不牺牲精度的前提下实现了强可解释性。此外，其校准集预测效率优于其他CP方法，同时输出结构一致的可解释预测集合。
原文摘要 · Abstract (English)
Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial complement to effectively support human experts during inference. This work proposes the Calibrated Hierarchical QPM (CHiQPM) which offers uniquely comprehensive global and local interpretability, paving the way for human-AI complementarity. CHiQPM achieves superior global interpretability by contrastively explaining the majority of classes and offers novel hierarchical explanations that are more similar to how humans reason and can be traversed to offer a built-in interpretable Conformal prediction (CP) method. Our comprehensive evaluation shows that CHiQPM achieves state-of-the-art accuracy as a point predictor, maintaining 99% accuracy of non-interpretable models. This demonstrates a substantial improvement, where interpretability is incorporated without sacrificing overall accuracy. Furthermore, its calibrated set prediction is competitively efficient to other CP methods, while providing interpretable predictions of coherent sets along its hierarchical explanation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。