首页> 外文会议>2016 International Conference on Biometrics >Face attribute prediction using off-the-shelf CNN features
【24h】

Face attribute prediction using off-the-shelf CNN features

机译:使用现成的CNN功能预测人脸属性

获取原文
获取原文并翻译 | 示例

摘要

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks - face localization, facial descriptor construction, and attribute classification - in a pipeline. As a typical classification problem, face attribute prediction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks.
机译:从野外的面部图像预测属性是一个具有挑战性的计算机视觉问题。为了从包含面部的图像中自动描述面部属性,传统上需要在管道中级联三个技术模块-面部定位,面部描述符构造和属性分类。作为典型的分类问题,已经使用深度学习解决了面部属性预测。当前的最新性能是通过使用两个经过级联的卷积神经网络(CNN)实现的,这些网络经过专门训练以学习人脸定位和属性描述。在本文中,我们尝试了一种使用CNN深度表示功能的替代方法。结合传统的人脸定位技术,我们使用经过训练可用于人脸识别的现成架构来构建人脸描述符。认识到可描述的面部属性是多种多样的,因此我们的面部描述符是从CNN的不同级别构造的,用于不同的属性,以最好地促进面部属性的预测。在两个大型数据集LFWA和CelebA上进行的实验表明,我们的方法完全可以与最新技术相提并论。我们的发现不仅证明了一种有效的面部属性预测方法,而且提出了一个重要的问题:如何利用现成的CNN表示的功能来完成新任务。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
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