This may be a more of a theoretical question. But, when calculating the saliency maps and the guided back prop, when calculating the loss to get the gradients, the output is used (of the class).
Is it how the loss needs to be calculated for saliency and guided back prop? Thank you.
This may be a more of a theoretical question. But, when calculating the saliency maps and the guided back prop, when calculating the loss to get the gradients, the output is used (of the class). Is it how the loss needs to be calculated for saliency and guided back prop? Thank you.