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={Ramprasaath R. Selvaraju and Michael Cogswell and Abhishek Das and Ramakrishna Vedantam and Devi Parikh and Dhruv Batra},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={618-626}
}
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. Our approach – Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any target concept (say logits for ‘dog’ or even a caption), flowing into the final convolutional layer to produce a coarse localization map highlighting the important regions in the image for predicting the concept. Unlike previous… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 51 REFERENCES

L

  • B. Zhou, A. Khosla
  • A., A. Oliva, and A. Torralba. Learning Deep…
  • 2016
Highly Influential
6 Excerpts

Similar Papers

Loading similar papers…