DMA Regularization: Enhancing Discriminability of Neural Networks by Decreasing the Minimal Angle

Most of the discriminative feature learning methods are specifically developed for metric learning, however, the effectiveness may be not obvious for other tasks. In this letter, we propose a novel discrimination regularization method for image classification, which enhances the intra-class compactness and inter-class discrepancy simultaneously, through decreasing the minimalangle (DMA) between the feature vector and any one of the weight vectors in classification layer. This method can robustly improve the discriminability and generalizability of neural networks and easily exert its effect by plugging the DMA regularization term into the loss function with negligible computational overhead. The DMA regularization is simple, efficient, and effective. Therefore, it can be used as a basic regularization method for models based on neural networks. We evaluate DMA by applying it to various modern models on CIFAR10, CIFAR100, and TinyImageNet datasets, decreasing the test error rate by 0.2-0.4%, 0.2-1.5%, and 0.3-0.4% respectively. Code is available at: https://github.com/wznpub/DMA_Regularization.