Semantic Correlations Loss: Improving Model Interpretability for Multi-class Classification

Xuezhi Tong, Rui Wang, Xiaochun Cao, Wenqi Ren

Abstract: Despite that convolutional neural networks (CNNs) have recently demonstrated high-quality object classification, the trained models suffer from their extreme unexplainability. In this paper, we propose a general method, named as semantic correlation loss, for introducing common-sense knowledge to CNN architectures. In contrast to traditional cross-entropy loss which only considers the ground-truth class, we exploit to be aware of the accuracy of all classes. By adding this simple add-on, current multi-class classification models are able to improve on the ability of “making mistakes reasonably”. In addition, a slight performance gain is also achieved. Experimental results on CUB-200-2011, CIFAR -10 and 100 are provided to demonstrate the efficacy of our proposed method. Moreover, this novel loss is able to be applied in any setting as long as the labels of training data are included in the common sense knowledge base.