Class GradCAMpp

monai/visualize/class_activation_maps.py:387–412

Computes Gradient-weighted Class Activation Mapping (Grad-CAM++). This implementation is based on: Chattopadhyay et al., Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks, https://arxiv.org/abs/1710.11063 See Also: - :py:class:`monai.vis

class GradCAMpp(GradCAM):
    """
    Computes Gradient-weighted Class Activation Mapping (Grad-CAM++).
    This implementation is based on:

        Chattopadhyay et al., Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks,
        https://arxiv.org/abs/1710.11063

    See Also:

        - :py:class:`monai.visualize.class_activation_maps.GradCAM`

    """

    def compute_map(self, x, class_idx=None, retain_graph=False, layer_idx=-1, **kwargs):  # type: ignore[override]
        _, acti, grad = self.nn_module(x, class_idx=class_idx, retain_graph=retain_graph, **kwargs)
        acti, grad = acti[layer_idx], grad[layer_idx]
        b, c, *spatial = grad.shape
        alpha_nr = grad.pow(2)
        alpha_dr = alpha_nr.mul(2) + acti.mul(grad.pow(3)).view(b, c, -1).sum(-1).view(b, c, *[1] * len(spatial))
        alpha_dr = torch.where(alpha_dr != 0.0, alpha_dr, torch.ones_like(alpha_dr))
        alpha = alpha_nr.div(alpha_dr + 1e-7)
        relu_grad = F.relu(cast(torch.Tensor, self.nn_module.score).exp() * grad)
        weights = (alpha * relu_grad).view(b, c, -1).sum(-1).view(b, c, *[1] * len(spatial))
        acti_map = (weights * acti).sum(1, keepdim=True)
        return F.relu(acti_map)