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.

本文提出了一种新的基于梯度的XAI方法，称为引导绝对梯度方法，用于显著图解释。我们利用正负梯度幅度，并采用梯度方差来区分噪声扣除的重要区域。我们还引入了一种名为ReCover And Predict（RCAP）的新型评估指标，考虑到解释的定位和视觉噪声水平的目标。我们使用RCAP指标和其他SOTA指标在三个案例研究中评估了引导绝对梯度方法，其中包括（1）ImageNet数据集与ResNet50模型；（2）International Skin Imaging Collaboration（ISIC）数据集与EfficientNet模型；（3）Places365数据集与DenseNet161模型。我们的方法超越了其他基于梯度的方法，展示了通过梯度幅度增强的显著图解释的质量。

引导绝对梯度：梯度大小对解释定位和显著性的影响