From Interpretable Filters to Predictions of Convolutional Neural Networks with Explainable Artificial Intelligence

TL;DR

This paper explores the interpretability of CNN filters in classifying Covid-19 from spectrograms using various XAI methods, aiming to demystify the black-box nature of CNNs.

Contribution

It introduces the cnnexplain model and applies multiple XAI techniques to interpret CNN features for Covid-19 detection from spectrograms, enhancing understanding of model decisions.

Findings

XAI methods highlight relevant features in spectrograms for Covid-19 detection.

Grad-CAM, LIME, and SmoothGrad provide complementary insights into CNN decision-making.

Interpretability aids in understanding CNN's focus on specific spectral features.

Abstract

Convolutional neural networks (CNN) are known for their excellent feature extraction capabilities to enable the learning of models from data, yet are used as black boxes. An interpretation of the convolutional filtres and associated features can help to establish an understanding of CNN to distinguish various classes. In this work, we focus on the explainability of a CNN model called as cnnexplain that is used for Covid-19 and non-Covid-19 classification with a focus on the interpretability of features by the convolutional filters, and how these features contribute to classification. Specifically, we have used various explainable artificial intelligence (XAI) methods, such as visualizations, SmoothGrad, Grad-CAM, and LIME to provide interpretation of convolutional filtres, and relevant features, and their role in classification. We have analyzed the explanation of these methods for Covid-19 detection using dry cough spectrograms. Explanation results obtained from the LIME, SmoothGrad, and Grad-CAM highlight important features of different spectrograms and their relevance to classification.