论文标题
加权游戏：评估可解释方法的质量
The Weighting Game: Evaluating Quality of Explainability Methods
论文作者
论文摘要
本文的目的是评估图像分类任务的解释热图的质量。为了评估解释性方法的质量，我们通过准确性和稳定性的角度来完成任务。 在这项工作中，我们做出以下贡献。首先，我们介绍了加权游戏，该游戏衡量了正确的类“分割掩码中包含的班级指导解释”。其次，我们使用缩放/平移变换引入了用于解释稳定性的度量，以测量具有相似内容的显着性图之间的差异。 使用这些新指标生产定量实验，以评估常用CAM方法提供的解释质量。不同模型架构之间的解释质量也形成了鲜明对比，发现突出了选择在选择解释性方法时考虑模型体系结构的必要性。
The objective of this paper is to assess the quality of explanation heatmaps for image classification tasks. To assess the quality of explainability methods, we approach the task through the lens of accuracy and stability. In this work, we make the following contributions. Firstly, we introduce the Weighting Game, which measures how much of a class-guided explanation is contained within the correct class' segmentation mask. Secondly, we introduce a metric for explanation stability, using zooming/panning transformations to measure differences between saliency maps with similar contents. Quantitative experiments are produced, using these new metrics, to evaluate the quality of explanations provided by commonly used CAM methods. The quality of explanations is also contrasted between different model architectures, with findings highlighting the need to consider model architecture when choosing an explainability method.
