Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value

• URL: http://arxiv.org/abs/2208.03608v2
• Date: Tue, 9 Aug 2022 04:09:30 GMT
• Title: Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value
• Authors: Quan Zheng, Ziwei Wang, Jie Zhou, and Jiwen Lu
• Abstract summary: We develop a novel visual explanation method called Shap-CAM based on class activation mapping. We demonstrate that Shap-CAM achieves better visual performance and fairness for interpreting the decision making process.
• Score: 86.69600830581912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explaining deep convolutional neural networks has been recently drawing increasing attention since it helps to understand the networks' internal operations and why they make certain decisions. Saliency maps, which emphasize salient regions largely connected to the network's decision-making, are one of the most common ways for visualizing and analyzing deep networks in the computer vision community. However, saliency maps generated by existing methods cannot represent authentic information in images due to the unproven proposals about the weights of activation maps which lack solid theoretical foundation and fail to consider the relations between each pixel. In this paper, we develop a novel post-hoc visual explanation method called Shap-CAM based on class activation mapping. Unlike previous gradient-based approaches, Shap-CAM gets rid of the dependence on gradients by obtaining the importance of each pixel through Shapley value. We demonstrate that Shap-CAM achieves better visual performance and fairness for interpreting the decision making process. Our approach outperforms previous methods on both recognition and localization tasks.

Related papers

• Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations [1.2891210250935146]
  We propose a novel approach to generate coarse visual explanations of networks designed to classify unstructured 3D data. Our method uses gradients flowing back to the final feature map layers and maps these values as contributions of the corresponding points in the input point cloud. The generality of our approach is tested on various point cloud classification networks, including'single object' networks PointNet, PointNet++, DGCNN, and a'scene' network VoteNet.
  arXiv  Detail & Related papers  (2022-07-26T15:42:08Z)
• Poly-CAM: High resolution class activation map for convolutional neural networks [88.29660600055715]
  saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction. This is because those maps are either low-resolution as for CAM [Zhou et al., 2016], or smooth as for perturbation-based methods [Zeiler and Fergus, 2014], or do correspond to a large number of widespread peaky spots. In contrast, our work proposes to combine the information from earlier network layers with the one from later layers to produce a high resolution Class Activation Map.
  arXiv  Detail & Related papers  (2022-04-28T09:06:19Z)
• 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)
• Enhancing Deep Neural Network Saliency Visualizations with Gradual Extrapolation [0.0]
  We propose an enhancement technique of the Class Activation Mapping methods like Grad-CAM or Excitation Backpropagation. Our idea, called Gradual Extrapolation, can supplement any method that generates a heatmap picture by sharpening the output.
  arXiv  Detail & Related papers  (2021-04-11T07:39:35Z)
• White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks [3.3959642559854357]
  Convolutional Neural Networks (CNNs) have demonstrated state of the art performance for the task of image classification. Several approaches have been proposed to explain to understand the reasoning behind a prediction made by a network. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision.
  arXiv  Detail & Related papers  (2021-04-06T14:40:00Z)
• Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring [26.434705114982584]
  Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. We introduce a solution to tackle this problem by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN's predictions.
  arXiv  Detail & Related papers  (2021-02-15T19:21:46Z)
• A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation [86.35434065681925]
  This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) Unlike existing designs, our approach focuses on modeling the temporal correlation between the sparse representations of consecutive video frames. Experimentation using the moving MNIST dataset shows that the proposed network outperforms a recently proposed state-of-the-art RPCA network in the task of video foreground-background separation.
  arXiv  Detail & Related papers  (2020-10-02T11:40:09Z)
• Visual Concept Reasoning Networks [93.99840807973546]
  A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. We propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. Our proposed model, VCRNet, consistently improves the performance by increasing the number of parameters by less than 1%.
  arXiv  Detail & Related papers  (2020-08-26T20:02:40Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations [15.067369314723958]
  We propose an objective measure to evaluate the reliability of explanations of deep models. Our approach is based on changes in the network's outcome resulting from the perturbation of input images in an adversarial way. We also propose a straightforward application of our approach to clean relevance maps, creating more interpretable maps without any loss in essential explanation.
  arXiv  Detail & Related papers  (2020-04-22T19:57:34Z)

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.