Search⌘ K
AI Features
Home
Courses
Master Explainable AI: Interpreting Image Classifier Decisions

X-GradCAM

Explore the X-GradCAM technique, an advanced class activation map method that improves interpretability of image classifiers by enforcing sensitivity and conservation axioms. Understand how X-GradCAM generates visual explanations that highlight important image regions for neural network predictions.

We'll cover the following...

Axiom-based GradCAM

Axiom-based GradCAM or X-GradCAM is an enhanced version of GradCAM that satisfies two explainability axioms—sensitivity and conservation.

Let's assume that Fl∈Rh×w\mathcal{F}_l \in \R^{h \times w} is the lthl^{th} feature map obtained from the penultimate convolutional layer (hh and ww are the height and width of the feature map) and Fl(i,j)\mathcal{F}_l(i,j) represents the activation of the (i,j)th(i,j)^{th} neuron in the ...