Grad-cam: Visual explanations from deep networks via gradient-based localization
RR Selvaraju, M Cogswell, A Das… - Proceedings of the …, 2017 - openaccess.thecvf.com
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 approaches, Grad-CAM is applicable to a wide …
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 approaches, Grad-CAM is applicable to a wide …
Grad-CAM: visual explanations from deep networks via gradient-based localization
RR Selvaraju, M Cogswell, A Das, R Vedantam… - International journal of …, 2020 - Springer
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. Our approach—Gradient-weighted Class Activation Mapping (Grad-CAM), uses
the gradients of any target concept (say 'dog'in a classification network or a sequence of
words in captioning network) flowing into the final convolutional layer to produce a coarse
localization map highlighting the important regions in the image for predicting the concept …
of Convolutional Neural Network (CNN)-based models, making them more transparent and
explainable. Our approach—Gradient-weighted Class Activation Mapping (Grad-CAM), uses
the gradients of any target concept (say 'dog'in a classification network or a sequence of
words in captioning network) flowing into the final convolutional layer to produce a coarse
localization map highlighting the important regions in the image for predicting the concept …