GradCAM

Gradient-weighted CAM

A gradient-weighted CAM or Grad-CAM is another class activation map algorithm that uses the gradients of the predicted class propagating into the final convolutional layer to weigh the feature maps used for creating maps.

Let's assume that $\mathcal{F}_l \in \R^{h \times w}$ is the $l^{th}$ feature map obtained from the penultimate convolutional layer ($h$ and $w$ are the height and width of the feature map) and $\mathcal{F}_l(i,j)$ represents the activation of the $(i,j)^{th}$ neuron in the $l^{th}$ feature map (total $L$ feature maps in $\mathcal{F}$).

Now we compute the gradient $\mathcal{G}_l(i,j) = \nabla_{\mathcal{F_l(i,j)}} f^{k^*}(X)$ of the prediction score $f^{k^*}(X)$ with respect to the feature $\mathcal{F}_l(i,j)$. The gradient $\mathcal{G}_l(i,j) \in \R^{h \times w}$ is then average pooled across height and width to be used as weights in the CAM equation. This looks as follows: