Multi-Scale Interpretation Model for Convolutional Neural Networks: Building Trust Based on Hierarchical Interpretation

With the rapid development of deep learning models, their performances in various tasks have improved; meanwhile, their increasingly intricate architectures make them difficult to interpret. To tackle this challenge, model interpretability is essential and has been investigated in a wide range of applications. For end users, model interpretability can he used to build trust in the deployed machine learning models. For practitioners, interpretability plays a critical role in model explanation, model validation, and model improvement to develop a faithful model. In this paper, we propose a novel Multi-scale Interpretation (MINT) model for convolutional neural networks using both the perturbation-based and the gradient-based interpretation approaches. It learns the class-discriminative interpretable knowledge from the multi-scale perturbation of feature information in different layers of deep networks. The proposed MINT model provides the coarse-scale and the fine-scale interpretations for the attention in the deep layer and specific features in the shallow layer, respectively. Experimental results show that the MINT model presents the class-discriminative interpretation of the network decision and explains the significance of the hierarchical network structure.