A Metric to Compare Pixel-Wise Interpretation Methods for Neural Networks

Abstract

There are various pixel-based interpretation methods such as saliency map, gradient×input, DeepLIFT, integrated-gradient-n, etc. However, it is difficult to compare their performance as it involves human cognitive processes. We propose a metric that can quantify the distance from the importance scores of the interpretation methods to human intuition. We create a new dataset by adding a simple and small image, named as a stamp, to the original images. The importance scores for the deep neural networks to classify the stamped and regular images are calculated. Ideally, the pixel-based interpretation has to successfully select the stamps. Previous methods to compare different interpretation methods are useful only when the scale of the importance scores is the same. Whereas, we standardize the importance scores and define the measure to ideal scores. Our proposed method can quantitatively measure how the interpretation methods are close to human intuition.

Visualizing Transform Relations of Multilayers in Deep Neural Networks for ISAR Target Recognition

“…This problem draws a great attention and many works of network interpretation are focused on it recently. Jay et al [23] propose a method to compare several interpretation methods for DNNs model based on human intuition. The visualization of DNNs for target recognition can help understand how the model descriminates the input sample and find out whether the key points are from the target itself or the differences from the background.…”