MI CAM: Mutual Information Weighted Activation Mapping for Causal Visual Explanations of Convolutional Neural Networks
This addresses the need for causal visual explanations in critical applications like healthcare and automated systems, though it appears incremental as it builds on existing activation mapping approaches.
The paper tackles the problem of explaining convolutional neural network decisions by proposing MI CAM, a post-hoc visual explanation method that uses mutual information to weight activation maps, achieving performance on par with state-of-the-art methods and outperforming some in qualitative and quantitative measures.
With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network provides specific inferences. This paper proposes a novel post-hoc visual explanation method called MI CAM based on activation mapping. Differing from previous class activation mapping based approaches, MI CAM produces saliency visualizations by weighing each feature map through its mutual information with the input image and the final result is generated by a linear combination of weights and activation maps. It also adheres to producing causal interpretations as validated with the help of counterfactual analysis. We aim to exhibit the visual performance and unbiased justifications for the model inferencing procedure achieved by MI CAM. Our approach works at par with all state-of-the-art methods but particularly outperforms some in terms of qualitative and quantitative measures. The implementation of proposed method can be found on https://anonymous.4open.science/r/MI-CAM-4D27