...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >Discriminative metric learning for face verification using enhanced Siamese neural network
【24h】

Discriminative metric learning for face verification using enhanced Siamese neural network

机译：使用增强型暹罗神经网络对脸部验证的鉴别度量学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

Although face verification algorithms have made great success under controlled conditions in recent years, there's plenty of room at its performance under uncontrolled real-world due to lack of discriminative feature representation ability. From the perspective of metric learning, we proposed a context-aware based Siamese neural network (CASNN) to learn a simple yet powerful network for face verification task to enhance its discriminative feature representation ability. Firstly, a context-aware module is used to automatically focus on the key area of the input facial images without irrelevant background area. Then we design a Siamese network equipped with center-classification loss to compress intra-class features and enlarge between-class ones for discriminative metric learning. Finally, we propose a quantitative indicator named "D-score" to show the discriminative representation ability of the learnt features from different methods. The extensive experiments are conducted on LFW dataset, YouTube Face dataset (YTF) and real-world dataset. The results confirm that CASNN outperforms some state-of-the-art deep learning-based face verification methods.
机译：虽然近年来，脸部验证算法在受控条件下取得了巨大成功，但由于缺乏歧视特征表示能力，在不受控制的现实世界中的性能下有足够的空间。从度量学习的角度来看，我们提出了一种基于背景知识的暹罗神经网络（Casnn），用于学习用于面部验证任务的简单且强大的网络，以增强其鉴别性特征表示能力。首先，上下文感知模块用于自动聚焦在没有无关背景区域的输入面部图像的关键区域。然后我们设计一个配备中心分类损失的暹罗网络，以压缩课外功能，并在课堂上放大歧视度量学习。最后，我们提出了名为“D-Score”的定量指标，以显示来自不同方法的学习功能的辨别表达能力。广泛的实验是在LFW数据集，YouTube面部数据集（YTF）和现实世界数据集上进行的。结果证实，Casnn优于基于最先进的深度学习的面部验证方法。

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号