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

• URL: http://arxiv.org/abs/2404.15564v1
• Date: Tue, 23 Apr 2024 23:26:02 GMT
• Title: Guided AbsoluteGrad: Magnitude of Gradients Matters to Explanation's Localization and Saliency
• Authors: Jun Huang, Yan Liu,
• Abstract summary: We propose a gradient-based XAI method called Guided AbsoluteGrad for saliency map explanations. We introduce a novel evaluation metric named ReCover And Predict (RCAP), which considers the localization and visual noise level objectives. We evaluate Guided AbsoluteGrad with seven gradient-based XAI methods using the RCAP metric and other SOTA metrics in three case studies.
• Score: 10.786952260623002
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• Deep Manifold Learning with Graph Mining [80.84145791017968]
  We propose a novel graph deep model with a non-gradient decision layer for graph mining. The proposed model has achieved state-of-the-art performance compared to the current models.
  arXiv  Detail & Related papers  (2022-07-18T04:34:08Z)
• Rethinking gradient weights' influence over saliency map estimation [0.0]
  Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. We propose a global guidance map to rectify the weighted aggregation operation during saliency estimation. The proposed scheme achieves significant improvement over the test images from the ImageNet, MS-COCO 14, and PASCAL VOC 2012 datasets.
  arXiv  Detail & Related papers  (2022-07-12T08:14:57Z)
• Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks [7.71412567705588]
  Class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. We propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimize the gradients derived from the backpropagation. The framework of Abs-CAM is divided into two phases: generating initial saliency map and generating final saliency map.
  arXiv  Detail & Related papers  (2022-07-08T02:06:46Z)
• Geometrically Guided Integrated Gradients [0.3867363075280543]
  We introduce an interpretability method called "geometrically-guided integrated gradients" Our method explores the model's dynamic behavior from multiple scaled versions of the input and captures the best possible attribution for each input. We also propose a "model perturbation" sanity check to complement the traditionally used "model randomization" test.
  arXiv  Detail & Related papers  (2022-06-13T05:05:43Z)
• Gradient Correction beyond Gradient Descent [63.33439072360198]
  gradient correction is apparently the most crucial aspect for the training of a neural network. We introduce a framework (textbfGCGD) to perform gradient correction. Experiment results show that our gradient correction framework can effectively improve the gradient quality to reduce training epochs by $sim$ 20% and also improve the network performance.
  arXiv  Detail & Related papers  (2022-03-16T01:42:25Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• Investigating Saturation Effects in Integrated Gradients [5.366801257602863]
  We propose a variant of IntegratedGradients which primarily captures gradients in unsaturated regions. We find that this attribution technique shows higher model faithfulness and lower sensitivity to noise com-pared with standard Integrated Gradients.
  arXiv  Detail & Related papers  (2020-10-23T22:48:02Z)
• Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement [54.29252286561449]
  We propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results.
  arXiv  Detail & Related papers  (2020-07-21T04:59:15Z)
• Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution [70.78655569298923]
  Integrated Gradients as an attribution method for deep neural network models offers simple implementability. It suffers from noisiness of explanations which affects the ease of interpretability. The SmoothGrad technique is proposed to solve the noisiness issue and smoothen the attribution maps of any gradient-based attribution method.
  arXiv  Detail & Related papers  (2020-04-22T10:43:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.