Abstract
This paper proposes a new gradient-based XAI method called Guided AbsoluteGrad for saliency map explanations. We utilize both positive and negative gradient magnitudes and employ gradient variance to distinguish the important areas for noise deduction. We also introduce a novel evaluation metric named ReCover And Predict (RCAP), which considers the Localization and Visual Noise Level objectives of the explanations. We propose two propositions for these two objectives and prove the necessity of evaluating them. We evaluate Guided AbsoluteGrad with seven gradient-based XAI methods using the RCAP metric and other SOTA metrics in three case studies: (1) ImageNet dataset with ResNet50 model; (2) International Skin Imaging Collaboration (ISIC) dataset with EfficientNet model; (3) the Places365 dataset with DenseNet161 model. Our method surpasses other gradient-based approaches, showcasing the quality of enhanced saliency map explanations through gradient magnitude.
Abstract (translated)
本文提出了一种名为Guided AbsoluteGrad的新XAI方法,用于解释显著性图。我们利用正负梯度幅度并采用梯度方差来区分重要的噪声推断区域。我们还引入了一个名为ReCover And Predict(RCAP)的新评估指标,它考虑了解释的局部化和视觉噪声水平目标。我们提出了这两个目标的两个命题,并证明评估它们是必要的。我们在三个案例研究中使用RCAP和其他SOTA指标评估Guided AbsoluteGrad:(1)使用ResNet50模型的ImageNet数据集;(2)使用EfficientNet模型的ISIC数据集;(3)使用DenseNet161模型的Places365数据集。我们的方法超越了其他基于梯度的方法,通过梯度幅度展示了增强显著性图解释的质量。
URL
https://arxiv.org/abs/2404.15564
