Diagnostic tool for deep learning similarity models

A system for generating a saliency map for a computer vision application, the system comprising:

• a processor;
• and
• a computer-readable medium storing instructions that are operative upon execution by the processor to:
• receive a baseline image and a test image;
• determine, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image;
• based on at least determining the first similarity, determine, for the test image, a first activation map for at least one CNN layer;
• based on at least determining the first similarity, determine, for the test image, a first gradient map for the at least one CNN layer;
• and
• generate a first saliency map as a first element-wise function of the first activation map and the first gradient map.

One or more computer storage devices having computer-executable instructions stored thereon, which, on execution by a computer, cause the computer to perform operations comprising:

• receiving a baseline image and a test image;
• determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image;
• based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer;
• based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer;
• and
• generating a first saliency map as a first element-wise function of the first activation map and the first gradient map.