Skip to content
ml-recall

#occlusion

1 question from Explainable AI

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedExplainable AI

To build an occlusion map for a 32×3232 \times 32 image, you slide an 8×88 \times 8 grey patch over it with a stride of 4 pixels in both directions, keeping the patch inside the image, and run the classifier once per patch position. How many occluded images are evaluated?

a whole number