Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models
This addresses the problem of model interpretability for AI-assisted applications, though it appears incremental as it builds on existing interpretability methods.
The paper tackles the lack of interpretability in CNN models by proposing a hybrid CNN-interpreter that combines local and global interpretability methods, enabling detailed and consistent monitoring of model context during learning.
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.