Relevance Regularization of Convolutional Neural Network for Interpretable Classification

Chae Hwa Yoo, Nayoung Kim, Je-Won Kang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 40-43

Conventional end-to-end learning algorithm considers only the final prediction output and ignores layer-wise relational reasoning during the training. In this paper, we propose to use a forward and backward interacted-activation (FBI) loss function that regularizes training a CNN so that the prediction model can provide interpretable results for classification. From our best knowledge, the proposed algorithm is the first work to use a regularization function without any prior knowledge or pre-defined terms to allow for a CNN to be more explainable. It is demonstrated with quantitative and qualitative analysis that the proposed technique can be used for efficiently train a CNN with more interpretability, applied to a well-known classification problem.