Automatic food recognition is the very first step towards the passive dietary monitoring. In this paper, we address the problem of food recognition by mining discriminative food regions. Taking inspiration from Adversarial Erasing, a strategy that progressively discovers discriminative object regions for the weakly supervised semantic segmentation, we propose a novel network architecture in which a primary network maintains the base accuracy of classifying an input image, an auxiliary network adversarially mines discriminative food regions, and a region network classifies the resulting mined regions. The global (original input image) and the local (mined region) representations are then integrated for the final prediction. The proposed architecture denoted as PAR-Net is end-to-end trainable, and highlights discriminative regions in an online fashion. In addition, we introduce a new fine-grained food dataset named as Sushi-50, which consists of 50 different sushi categories. Extensive experiments have been conducted to evaluate the proposed approach. On three food datasets chosen (Food-101, Vireo-172, and Sushi-50), our method performs consistently and achieves state-of-the-art results (top-1 testing accuracy of 90.4%, 90.2%, 92.0%, respectively) compared with other existing approaches.