PickPatch: A Regularization Method for Deep Face Recognition. (March 2020)

• Record Type: Journal Article
• Authors: Sun, Linjun; He, Wei; Ning, Xin; Li, Weijun; Shi, Yuan
• Is Part Of: Journal of physics. Volume 1487(2020)
• Publication Date: 2020-03
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1487/1/012024
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: This paper proposes a simple and efficient regularization method, called PickPatch, for face recognition based on a deep convolutional neural network (DCNN). The proposed method randomly selects patches in the input face image and the intermediate feature maps as the activation region according to facial landmarks during the training phase. PickPatch is an approximation method that trains a series of models for different face patches and provides a combined model. This strategy introduces the idea of model combination for multiple face patches but does not change the model structure, which is both simple and efficient. Experiments on the public LFW database demonstrate that the proposed regularization method based on current deep convolutional neural networks can achieve obvious improvements of face recognition accuracy.