Deep convolutional neural networks (CNNs) trained with the softmax loss have achieved remarkable successes in a number of close-set recognition problems, e.g. object recognition, action recognition, etc. Unlike these close-set tasks, face recognition is an open-set problem where the testing classes (persons) are usually different from those in training. This paper addresses the open-set property of face recognition by developing the center loss. Specifically, the center loss simultaneously learns a center for each class, and penalizes the distances between the deep features of the face images and their corresponding class centers. Training with the center loss enables CNNs to extract the deep features with two desirable properties: inter-class separability and intra-class compactness. In addition, we extend the center loss in two aspects. First, we adopt parameter sharing between the softmax loss and the center loss, to reduce the extra parameters introduced by centers. Second, we generalize the concept of center from a single point to a region in embedding space, which further allows us to account for intra-class variations. The advanced center loss significantly enhances the discriminative power of deep features. Experimental results show that our method achieves high accuracies on several important face recognition benchmarks, including Labeled Faces in the Wild, YouTube Faces, IJB-A Janus, and MegaFace Challenging 1.

中文翻译：

---

深度人脸识别中心损失的综合研究

使用 softmax loss 训练的深度卷积神经网络 (CNN) 在许多封闭集识别问题中取得了显着的成功，例如对象识别、动作识别等。 与这些封闭集任务不同，人脸识别是一个开放集问题其中测试类（人）通常与培训中的类（人）不同。本文通过开发中心损失来解决人脸识别的开放集特性。具体来说，中心损失同时为每个类学习一个中心，并惩罚人脸图像的深层特征与其对应的类中心之间的距离。使用中心损失进行训练使 CNN 能够提取具有两个理想属性的深层特征：类间可分离性和类内紧凑性。此外，我们在两个方面扩展了中心损失。第一的，我们在 softmax 损失和中心损失之间采用参数共享，以减少中心引入的额外参数。其次，我们将中心的概念从单个点推广到嵌入空间中的一个区域，这进一步允许我们考虑类内变化。高级中心损失显着增强了深度特征的判别能力。实验结果表明，我们的方法在几个重要的人脸识别基准测试中都取得了很高的准确率，包括 Labeled Faces in the Wild、YouTube Faces、IJB-A Janus 和 MegaFace Challenging 1。这进一步使我们能够解释类内变化。高级中心损失显着增强了深度特征的判别能力。实验结果表明，我们的方法在几个重要的人脸识别基准测试中都取得了很高的准确率，包括 Labeled Faces in the Wild、YouTube Faces、IJB-A Janus 和 MegaFace Challenging 1。这进一步使我们能够解释类内变化。高级中心损失显着增强了深度特征的判别能力。实验结果表明，我们的方法在几个重要的人脸识别基准测试中取得了很高的准确率，包括 Labeled Faces in the Wild、YouTube Faces、IJB-A Janus 和 MegaFace Challenging 1。