Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities. The state-of-the-art (SOTA) solutions utilise normalised Softmax loss with additive and/or multiplicative margins. Despite being popular, these Softmax+margin based losses are not theoretically motivated and the effectiveness of a margin is justified only intuitively. In this work, we utilise an alternative framework that offers a more direct mechanism of achieving discrimination among the features of various identities. We propose a novel loss that is equivalent to a triplet loss with proxies and an implicit mechanism of hard-negative mining. We give theoretical justification that minimising the proposed loss ensures a minimum separability between all identities. The proposed loss is simple to implement and does not require heavy hyper-parameter tuning as in the SOTA solutions. We give empirical evidence that despite its simplicity, the proposed loss consistently achieves SOTA performance in various benchmarks for both high-resolution and low-resolution FR tasks.
翻译:使用深层进化神经网络(DCNN)的面部识别(FR)近年来取得了显著成功。基于DCNN的FR的一个关键要素是适当设计一种确保不同身份之间区别的损失功能。最先进的(SOTA)解决方案利用添加和(或)倍增效应的正常软体损失。尽管很受欢迎,但这些基于Softmax+margin的亏损在理论上并非出于动机,而差值的有效性只能凭直觉来证明。在这项工作中,我们使用一个替代框架,提供一种更直接的机制,实现不同身份特征特征之间的区别。我们提出了相当于代号为三重损失和硬反式采矿隐含机制的新损失。我们从理论上提出理由,将拟议的损失最小化确保所有身份之间的最小化。拟议的亏损很容易实施,而且不需要像SOTA解决方案那样的大幅超度调整。我们提供经验证据,证明尽管提议的损失是简单化的,但拟议的损失始终在高分辨率和低分辨率的FR任务的各种基准中达到SOTA的绩效。