评估视觉解释方法在噪声下的稳定性，提出可靠可衡量的解释鲁棒性指标。
Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
- 设计新指标衡量CAM在噪声下的稳定性和响应性。
- 发现不同CAM方法对噪声敏感度差异显著，受数据集影响大。
- 适合关注模型解释可信度的研究者与应用开发者。
类激活图（CAM）是深度学习模型可视化关键区域的重要方法，但其对各类噪声的鲁棒性尚未深入研究。本文系统评估了多种CAM方法在不同噪声扰动下，于多个模型架构与数据集上的表现。通过分析不同噪声类型对解释结果的影响，揭示了各CAM方法在噪声敏感性上的显著差异，并考察了数据集特性对解释稳定性的作用。研究提出一个鲁棒性度量，包含两个核心属性：一致性（输入扰动不改变预测类别时解释的稳定性）和响应性（对预测变化的敏感度）。该指标在多模型、多扰动、多数据集上进行实证验证，并辅以统计检验，证明其适用性与有效性。
原文摘要 · Abstract (English)
Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of various CAM methods for different noise perturbations across multiple architectures and datasets. By analyzing the influence of different noise types on CAM explanations, we assess the susceptibility to noise and the extent to which dataset characteristics may impact explanation stability. The findings highlight considerable variability in noise sensitivity for various CAMs. We propose a robustness metric for CAMs that captures two key properties: consistency and responsiveness. Consistency reflects the ability of CAMs to remain stable under input perturbations that do not alter the predicted class, while responsiveness measures the sensitivity of CAMs to changes in the prediction caused by such perturbations. The metric is evaluated empirically across models, different perturbations, and datasets along with complementary statistical tests to exemplify the applicability of our proposed approach.
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。