Learning the discriminative features of different faces is an important task in face recognition. By extracting face features with neural networks, it becomes easy to measure the similarity of different face images, which makes face recognition possible. To enhance a neural network’s face feature separability, incorporating an angular margin during training is common practice. The state-of-the-art loss functions CosFace and ArcFace apply fixed margins between the weights of classes to enhance the inter-class separation of face features. Since the distribution of samples in the training set is uneven, the similarities between different identities are unequal. Therefore, using an inappropriately fixed angular margin may lead to problems such as that the model has difficulty converging or that the face features are not sufficiently discriminative. It is more intuitive to use adaptive angular margins are angular adaptive, which can increase as the angles between classes increase. In this paper, we propose a new angular margin loss named X2-Softmax. X2-Softmax loss has adaptive angular margins, which increase as the angle between different classes increases. The angular adaptive margin ensures model flexibility and effectively improves the effect of face recognition. We trained a neural network with X2-Softmax loss on the MS1Mv3 dataset and tested it on several evaluation benchmarks to demonstrate the effectiveness and superiority of our loss function.

中文翻译：

---

X2-Softmax：人脸识别的边缘自适应损失函数

学习不同人脸的判别特征是人脸识别中的一项重要任务。通过用神经网络提取人脸特征，可以很容易地衡量不同人脸图像的相似度，从而使人脸识别成为可能。为了增强神经网络的面部特征可分离性，在训练期间结合角度边缘是常见的做法。最先进的损失函数 CosFace 和 ArcFace 在类权重之间应用固定边距，以增强人脸特征的类间分离。由于训练集中样本分布不均匀，不同身份之间的相似度也不相等。因此，使用不适当的固定角度裕量可能会导致模型难以收敛或人脸特征辨别力不够等问题。更直观的是使用自适应角度边距是角度自适应的，它可以随着类之间角度的增加而增加。在本文中，我们提出了一种新的角度边缘损失，名为 X2-Softmax。 X2-Softmax 损失具有自适应角度裕度，随着不同类别之间角度的增加而增加。角度自适应余量保证了模型的灵活性，有效提高了人脸识别的效果。我们在 MS1Mv3 数据集上训练了具有 X2-Softmax 损失的神经网络，并在多个评估基准上对其进行了测试，以证明我们的损失函数的有效性和优越性。