Guided AbsoluteGrad: Magnitude of Gradients Matters to Explanation's Localization and Saliency

arXiv:2404.15564v1 Announce Type: cross
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 …

abstract arxiv cs.ai cs.cv cs.hc cs.lg evaluation gradient localization map negative noise novel paper positive type variance xai