Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

@article{Selvaraju2017GradCAMVE,
  title={Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization},
  author={R. R. Selvaraju and Michael Cogswell and Abhishek Das and Ramakrishna Vedantam and D. Parikh and Dhruv Batra},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={618-626}
}
  • R. R. Selvaraju, Michael Cogswell, +3 authors Dhruv Batra
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • We propose a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. [...] Key Method We combine Grad-CAM with existing fine-grained visualizations to create a high-resolution class-discriminative visualization, Guided Grad-CAM, and apply it to image classification, image captioning, and visual question answering (VQA) models, including ResNet-based architectures. In the context of image classification…Expand Abstract
    1,175 Citations
    Understanding Individual Decisions of CNNs via Contrastive Backpropagation
    • 16
    • Highly Influenced
    • PDF
    U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps
    • 16
    • PDF
    Towards Visually Explaining Variational Autoencoders
    • Wenqian Liu, R. Li, +5 authors O. Camps
    • Computer Science
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    • 7
    • PDF
    Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
    • 9
    • PDF
    NormGrad: Finding the Pixels that Matter for Training
    • 2
    • PDF
    Explaining Visual Classification using Attributes
    A Step Towards Exposing Bias in Trained Deep Convolutional Neural Network Models
    Interpretable R-CNN
    • 14

    References

    SHOWING 1-10 OF 56 REFERENCES
    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
    • 1,681
    • PDF
    Learning Deep Features for Discriminative Localization
    • 2,703
    • PDF
    Self-taught object localization with deep networks
    • 104
    • PDF
    Striving for Simplicity: The All Convolutional Net
    • 2,252
    • Highly Influential
    • PDF
    Visualizing Deep Convolutional Neural Networks Using Natural Pre-images
    • 281
    • PDF
    Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
    • 2,815
    • Highly Influential
    • PDF
    Hierarchical Question-Image Co-Attention for Visual Question Answering
    • 776
    • PDF
    DenseCap: Fully Convolutional Localization Networks for Dense Captioning
    • 720
    • Highly Influential
    • PDF
    Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
    • 2,283
    • PDF
    Network In Network
    • 3,113
    • PDF