论文标题
损失功能搜索面部识别
Loss Function Search for Face Recognition
论文作者
论文摘要
在面部识别中，设计基于边距的（例如，角度，添加剂，添加角度边缘）软效果损耗功能在学习判别特征中起着重要作用。但是，这些手工制作的启发式方法是最佳的，因为它们需要大量努力来探索大型设计空间。最近，已经得出了用于损耗功能搜索方法AM-LFS的汽车，该方法利用强化学习在训练过程中搜索损失功能。但是它的搜索空间是复杂且不稳定的，从而阻碍了它的优势。在本文中，我们首先分析增强特征歧视的关键实际上是\ textbf {如何减少softmax概率}。然后，我们为当前基于边缘的软磁损失设计了一个统一的公式。因此，我们定义了一个新颖的搜索空间，并开发了一种奖励引导的搜索方法，以自动获得最佳候选人。各种面部识别基准的实验结果证明了我们方法对最先进的替代方案的有效性。
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.
