Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models

TL;DR

This paper introduces a hybrid CNN-interpreter that combines local and global interpretability methods, providing comprehensive insights into CNN models' internal logic and feature interactions for better understanding and monitoring.

Contribution

It proposes a novel hybrid interpretability framework with an original forward propagation mechanism and global analysis, applicable across various CNN architectures.

Findings

Effective local interpretability through layer-specific analysis

Global interpretability reveals feature correlations and filter importance

Applicable to multiple CNN model structures

Abstract

Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of AI-assisted applications. There have been many works on input interpretability focusing on analyzing the input-output relations, but the internal logic of models has not been clarified in the current mainstream interpretability methods. In this study, we propose a novel hybrid CNN-interpreter through: (1) An original forward propagation mechanism to examine the layer-specific prediction results for local interpretability. (2) A new global interpretability that indicates the feature correlation and filter importance effects. By combining the local and global interpretabilities, hybrid CNN-interpreter enables us to have a solid understanding and monitoring of model context during the whole learning process with detailed and consistent representations. Finally, the proposed interpretabilities have been demonstrated to adapt to various CNN-based model structures.