用互信息提升神经网络解释力，让模型决策更可信。
Analysis of Information Theory for Explainable AI
- 基于输入图像与输出结果的互信息加权特征图
- 在多个指标上达到顶尖水平，部分优于现有方法
- 提供因果解释，适合需可信AI的医疗等场景
随着机器视觉广泛应用于医疗、自动电厂等关键领域，人们越来越关注卷积神经网络内部机制及其推理依据。本文提出一种新的后处理可视化解释方法MI CAM，通过特征图与输入图像及最终输出之间的互信息进行加权，生成显著性图。该方法区别于传统类激活映射，以线性组合方式融合权重与激活图，实现因果性解释，并通过反事实分析验证其合理性。实验表明，MI CAM在视觉表现和无偏解释方面均表现优异，性能与当前最优方法相当，部分指标显著超越现有方法。
原文摘要 · Abstract (English)
With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network provides specific inferences. This paper proposes a novel post-hoc visual explanation method called MI CAM based on activation mapping. Differing from previous class activation mapping based approaches, MI CAM produces saliency visualizations by weighing each feature map through its mutual information with the input image and the final result is generated by a linear combination of weights and activation maps. It also adheres to producing causal interpretations as validated with the help of counterfactual analysis. We aim to exhibit the visual performance and unbiased justifications for the model inferencing procedure achieved by MI CAM. Our approach works at par with all state-of-the-art methods but particularly outperforms some in terms of qualitative and quantitative measures.
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。