用博弈论解释神经网络决策，让可视化更精准可靠。
CAMs as Shapley Value-based Explainers
- 将神经网络预测建模为合作博弈，基于沙普利值设计新解释方法。
- 在ImageNet上12个模型验证，显著提升可视化精度与理论可靠性。
- 适合关注可解释性、模型调试与理论严谨性的研究者。
类激活映射（CAM）方法广泛用于可视化神经网络决策，但其内在机制仍不明确。为增强对CAM方法的理解并提升可解释性，本文提出内容保留博弈论（CRG）解释框架，将神经网络预测过程建模为合作博弈，阐明了GradCAM和HiResCAM的理论基础。在此框架下，我们开发了ShapleyCAM，利用梯度与海森矩阵提供更精确、理论更坚实的可视化解释。由于精确沙普利值计算不可行，ShapleyCAM采用合作博弈效用函数的二阶泰勒展开，获得闭式表达式。此外，提出残差软最大目标类（ReST）效用函数，解决预-软最大和后-软最大得分的局限性。在ImageNet验证集上对12个主流网络的大量实验表明，ShapleyCAM及其变体有效。研究成果不仅推进了CAM可解释性，还弥合了启发式驱动的CAM方法与计算密集型沙普利值方法之间的差距。代码已开源。
原文摘要 · Abstract (English)
Class Activation Mapping (CAM) methods are widely used to visualize neural network decisions, yet their underlying mechanisms remain incompletely understood. To enhance the understanding of CAM methods and improve their explainability, we introduce the Content Reserved Game-theoretic (CRG) Explainer. This theoretical framework clarifies the theoretical foundations of GradCAM and HiResCAM by modeling the neural network prediction process as a cooperative game. Within this framework, we develop ShapleyCAM, a new method that leverages gradients and the Hessian matrix to provide more precise and theoretically grounded visual explanations. Due to the computational infeasibility of exact Shapley value calculation, ShapleyCAM employs a second-order Taylor expansion of the cooperative game's utility function to derive a closed-form expression. Additionally, we propose the Residual Softmax Target-Class (ReST) utility function to address the limitations of pre-softmax and post-softmax scores. Extensive experiments across 12 popular networks on the ImageNet validation set demonstrate the effectiveness of ShapleyCAM and its variants. Our findings not only advance CAM explainability but also bridge the gap between heuristic-driven CAM methods and compute-intensive Shapley value-based methods. The code is available at \url{https://github.com/caihuaiguang/pytorch-shapley-cam}.
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。