在人脸识别领域中，建立类似于附加角余量的softmax损失函数对于特征识别的学习效果非常重要。但由于这些手动操作的启发式需要耗费大量的精力来探索较大的设计空间，所以效果并不理想。最近，一种基于自动机器学习方法的损失函数搜索算法AM-LFS被提出，该方法在训练过程中利用强化学习方法来搜索损失函数。但其搜索空间复杂且不稳定，因此效果并不优越。在本文中，我们首先分析出增强特征识别效果的关键是降低softmax的概率。然后，我们为当前基于角向量的softmax损失函数设置了统一的公式。因此，我们定义出一个新颖搜索空间，并开发了一种基于奖励引导的搜索算法来自动获取最佳候选人。通过在各类面部识别标准上进行测试，结果表明该算法比起其最优替代方法要更加有效。

原文题目：Loss Function Search for Face Recognition

原文：In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features. However, these hand-crafted heuristic methods are sub-optimal because they require much effort to explore the large design space. Recently, an AutoML for loss function search method AM-LFS has been derived, which leverages reinforcement learning to search loss functions during the training process. But its search space is complex and unstable that hindering its superiority. In this paper, we first analyze that the key to enhance the feature discrimination is actually \textbf{how to reduce the softmax probability}. We then design a unified formulation for the current margin-based softmax losses. Accordingly, we define a novel search space and develop a reward-guided search method to automatically obtain the best candidate. Experimental results on a variety of face recognition benchmarks have demonstrated the effectiveness of our method over the state-of-the-art alternatives.

原文作者：Xiaobo Wang, Shuo Wang, Cheng Chi, Shifeng Zhang, Tao Mei

原文地址：https://arxiv.org/abs/2007.06542