• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Image Processing >LEVERAGING MID-LEVEL DEEP REPRESENTATIONS FOR PREDICTING FACE ATTRIBUTES IN THE WILD
【24h】

LEVERAGING MID-LEVEL DEEP REPRESENTATIONS FOR PREDICTING FACE ATTRIBUTES IN THE WILD

机译：利用中级深度表示来预测野外的面部属性

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Predicting facial attributes from faces in the wild is very challenging due to pose and lighting variations in the real world. The key to this problem is to build proper feature representations to cope with these unfavourable conditions. Given the success of Convolutional Neural Network (CNN) in image classification, the high-level CNN feature, as an intuitive and reasonable choice, has been widely utilized for this problem. In this paper, however, we consider the mid-level CNN features as an alternative to the high-level ones for attribute prediction. This is based on the observation that face attributes are different: some of them are locally oriented while others are globally defined. Our investigations reveal that the mid-level deep representations outperform the prediction accuracy achieved by the (fine-tuned) high-level abstractions. We empirically demonstrate that the mid-level representations achieve state-of-the-art prediction performance on CelebA and LFWA datasets. Our investigations also show that by utilizing the mid-level representations one can employ a single deep network to achieve both face recognition and attribute prediction.
机译：由于现实世界的姿势和照明变化，预测野外面部的面部属性非常具有挑战性。此问题的关键是构建适当的特征表示以应对这些不利条件。鉴于图像分类中的卷积神经网络（CNN）的成功，高级CNN特征，作为直观和合理的选择，已被广泛用于此问题。然而，在本文中，我们将中级CNN特征视为用于属性预测的高级元的替代方案。这是基于面部属性不同的观察结果：其中一些是在本地定向的，而其他人则是全局定义的。我们的调查表明，中级深度表示优于由（微调）高级抽象所实现的预测准确性。我们经验证明中级表示在Celeba和LFWA数据集上实现了最先进的预测性能。我们的调查还表明，通过利用中级表示，可以使用单个深网络来实现人脸识别和属性预测。

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