通过像素间信息传播，提升图像模型解释的准确性
Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach
- 将像素归因分数视为信息源，动态传播以捕捉局部结构
- 在多个指标上显著优于现有方法，收敛性有理论保证
- 可兼容任意归因方法，适合需要可靠解释的视觉任务
近年来，大量解释方法被用于解读深度神经网络（DNN）模型的决策过程。针对图像分类器，这些方法通常为图像中每个像素分配一个归因分数，以量化其对预测的贡献。然而，大多数方法独立处理像素的归因分数，尽管人类和DNN均通过同时分析一组密切相关像素来决策。因此，像素的归因分数应联合考虑其自身及其结构相似像素的影响。本文提出IProp方法，将每个像素的归因分数视为解释信息源，并通过跨所有像素的动态信息传播来解释图像预测。为建模信息传播，IProp采用马尔可夫奖励过程，确保收敛性，最终状态即为期望的像素归因分数。此外，IProp可与任何现有的基于归因的解释方法兼容。在多种解释方法和DNN模型上的大量实验表明，IProp在多个可解释性指标上显著提升了现有方法的表现。
原文摘要 · Abstract (English)
Numerous explanation methods have been recently developed to interpret the decisions made by deep neural network (DNN) models. For image classifiers, these methods typically provide an attribution score to each pixel in the image to quantify its contribution to the prediction. However, most of these explanation methods appropriate attribution scores to pixels independently, even though both humans and DNNs make decisions by analyzing a set of closely related pixels simultaneously. Hence, the attribution score of a pixel should be evaluated jointly by considering itself and its structurally-similar pixels. We propose a method called IProp, which models each pixel's individual attribution score as a source of explanatory information and explains the image prediction through the dynamic propagation of information across all pixels. To formulate the information propagation, IProp adopts the Markov Reward Process, which guarantees convergence, and the final status indicates the desired pixels' attribution scores. Furthermore, IProp is compatible with any existing attribution-based explanation method. Extensive experiments on various explanation methods and DNN models verify that IProp significantly improves them on a variety of interpretability metrics.
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。