Additive Parameter for Deep Face Recognition
Additive Parameter for Deep Face Recognition
复制标题
深度人脸识别的附加参数
DOI：
10.1007/s40304-019-00198-z
复制
发表时间：
2020-06-01
影响因子：
0.9
通讯作者：
Yang, Zhouwang
中科院分区：
文献类型：
--
作者：
Rahman, Jamshaid Ui;Chen, Qing;Yang, Zhouwang
深度卷积神经网络（DCNN）的特征学习性能正在迅速提高，在许多应用中有了显着改进。最近的损失函数研究清楚地描述了更好的归一化有助于提高人脸识别（FR）的性能。基于不同的损失函数，已经提出了几种方法用于FR以获得鉴别特征。在本文中，我们提出了一个取决于乘法角裕度的加性参数，以提高特征嵌入的鉴别力，并且易于实现。在附加参数方法中，以特定的方式为角度softmax学习角度判别特征提供了作为角度边缘种子结果的幼苗元素的自动调整。我们在可用的数据集CASIA-WebFace上训练模型，我们在著名的基准测试YouTube Faces（YTF）和野外标记人脸（LFW）上的实验比各种最先进的方法获得了更好的性能。
The performance of feature learning for deep convolutional neural networks (DCNNs) is increasing promptly with significant improvement in numerous applications. Recent studies on loss functions clearly describing that better normalization is helpful for improving the performance of face recognition (FR). Several methods based on different loss functions have been proposed for FR to obtain discriminative features. In this paper, we propose an additive parameter depending on multiplicative angular margin to improve the discriminative power of feature embedding that can be easily implemented. In additive parameter approach, an automatic adjustment of the seedling element as the result of angular marginal seed is offered in a particular way for the angular softmax to learn angularly discriminative features. We train the model on publically available dataset CASIA-WebFace, and our experiments on famous benchmarks YouTube Faces (YTF) and labeled face in the wild (LFW) achieve better performance than the various state-of-the-art approaches.