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

@article{Selvaraju2019GradCAMVE,
  title={Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization},
  author={R. R. Selvaraju and Abhishek Das and Ramakrishna Vedantam and Michael Cogswell and D. Parikh and Dhruv Batra},
  journal={International Journal of Computer Vision},
  year={2019},
  volume={128},
  pages={336-359}
}
  • R. R. Selvaraju, Abhishek Das, +3 authors Dhruv Batra
  • Published 2019
  • Computer Science
  • International Journal of Computer Vision
  • 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 and explainable. [...] Key Method Unlike previous approaches, Grad-CAM is applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers (e.g.Expand Abstract
    1,682 Citations
    Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks.
    • 13
    • Highly Influenced
    Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
    • 208
    • PDF
    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
    • 1,175
    • PDF
    Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization
    • 9
    • Highly Influenced
    • PDF
    Adapting Grad-CAM for Embedding Networks
    • 4
    • Highly Influenced
    • PDF
    NAD: Neuron Activation based Divergence Maps for Weakly Supervised Object Localization
    Tell Me Where to Look: Guided Attention Inference Network
    • 154
    • PDF
    Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
    • 8
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 96 REFERENCES
    Fully Convolutional Networks for Semantic Segmentation
    • 7,734
    • PDF
    Network Dissection: Quantifying Interpretability of Deep Visual Representations
    • 556
    • PDF
    Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
    • 16
    • PDF
    Visualizing Deep Convolutional Neural Networks Using Natural Pre-images
    • 281
    • PDF
    Striving for Simplicity: The All Convolutional Net
    • 2,254
    • Highly Influential
    • PDF
    Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
    • 2,821
    • PDF
    Learning Deep Features for Discriminative Localization
    • 2,708
    • PDF
    Self-taught object localization with deep networks
    • 104
    • PDF
    Hierarchical Question-Image Co-Attention for Visual Question Answering
    • 779
    • PDF
    DenseCap: Fully Convolutional Localization Networks for Dense Captioning
    • 720
    • Highly Influential
    • PDF