A method for quadruplet sample selection in deep feature learning

Recently, the deep learning based feature learning methodologies have been developed to recognize the objects in fine-grained detail. In order to increase the discriminativeness and robustness of the utilized features, this paper proposes a sample selection methodology for the quadruplet based feature learning. The feature space is manipulated by using the hierarchical structure of the training set. In the training process, the quadruplets are selected by considering the distances between the samples in the feature space in order to improve the effectiveness of the training. We have shown by the experiments that the proposed method improves the fine-grained recognition accuracy.