Efficient Saliency Maps for Explainable AI

T. Nathan Mundhenk, Barry Chen, Gerald Friedland

Keywords: Saliency, XAI, Efficent, Information

TL;DR: An efficent method for determining which locations in an image are informative to a CNN.

Abstract: We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular gradient methods. It is also quantitatively similar or better in accuracy. Our technique works by measuring information at the end of each network scale. This is then combined into a single saliency map. We describe how saliency measures can be made more efficient by exploiting Saliency Map Order Equivalence. Finally, we visualize individual scale/layer contributions by using a Layer Ordered Visualization of Information. This provides an interesting comparison of scale information contributions within the network not provided by other saliency map methods. Our method is generally straight forward and should be applicable to the most commonly used CNNs. (Full source code is available at http://www.anonymous.submission.com).

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1911.11293/code)