The widespread use of mobile devices for all kind of transactions makes necessary reliable and real-time identity authentication, leading to the adoption of face recognition (FR) via the cameras embedded in such devices. Progress of deep Convolutional Neural Networks (CNNs) has provided substantial advances in FR. Nonetheless, the size of state-of-the-art architectures is unsuitable for mobile deployment, since they often encompass hundreds of megabytes and millions of parameters. We address this by studying methods for deep network compression applied to FR. In particular, we apply network pruning based on Taylor scores, where less important filters are removed iteratively. The method is tested on three networks based on the small SqueezeNet (1.24M parameters) and the popular MobileNetv2 (3.5M) and ResNet50 (23.5M) architectures. These have been selected to showcase the method on CNNs with different complexities and sizes. We observe that a substantial percentage of filters can be removed with minimal performance loss. Also, filters with the highest amount of output channels tend to be removed first, suggesting that high-dimensional spaces within popular CNNs are over-dimensionated.

翻译：移动设备在各类交易中的广泛应用使得可靠且实时的身份认证成为必要，这推动了通过此类设备内置摄像头进行人脸识别（FR）的普及。深度卷积神经网络（CNNs）的发展为人脸识别带来了显著进步。然而，当前最先进的网络架构因其通常包含数百兆字节和数百万参数，并不适合移动端部署。我们通过研究应用于人脸识别的深度网络压缩方法来解决这一问题。具体而言，我们采用基于泰勒分数的网络剪枝方法，迭代移除重要性较低的滤波器。该方法在基于轻量级SqueezeNet（124万参数）、流行的MobileNetv2（350万参数）和ResNet50（2350万参数）架构的三个网络上进行了测试。选择这些网络旨在展示该方法在不同复杂度与规模CNN上的适用性。实验表明，在性能损失最小的情况下可移除相当比例的滤波器。此外，具有最多输出通道的滤波器往往被优先移除，这表明主流CNN内部的高维空间存在过度维度化现象。