Heterogenous Output Regression Network for Direct Face Alignment

Heterogenous Output Regression Network for Direct Face Alignment
复制标题

用于直接面部对齐的异构输出回归网络

DOI:
10.1016/j.patcog.2020.107311
复制
发表时间:
2020-09
影响因子:
8
通讯作者:
Ling Shao
Ling Shao
中科院分区:
计算机科学1区
文献类型:
--
作者:
Xiantong Zhen;Mengyang Yu;Zehao Xiao;Lei Zhang;Ling Shao

文献摘要

参考文献

被引文献

相似文献

人脸对齐由于其广泛的应用,在计算机视觉领域得到了广泛的应用。在本文中,我们提出了一种新的学习结构,即异质输出回归网络(Hornet),用于人脸对齐,直接从图像中预测人脸标志点。Hornet基于内核近似,建立了一种新的紧凑的多层体系结构。具有余弦激活的非线性层解开了面部地标的图像和形状的表示之间的非线性关系。具有身份激活的线性层通过矩阵弹性网的低阶学习来显式地编码地标相关性。Hornet非常灵活,既可以使用预构建的特征表示法,也可以使用卷积架构进行端到端学习。Hornet利用了核方法在建模非线性方面的优势和神经网络在结构预测方面的优势。这种组合使其成为直接人脸对齐的有效和高效的方法。在五个野外数据集上的广泛实验表明,大黄蜂提供了高性能,并始终超过了最先进的方法。
Face alignment has gained great popularity in computer vision due to its wide-spread applications. In this paper, we propose a novel learning architecture,i.e., heterogenous output regression network (HORNet), for face alignment, which directly predicts facial landmarks from images. HORNet is based on kernel approximations and establishes a new compact multi-layer architecture. A nonlinear layer with cosine activations disentangles nonlinear relationships between representations of images and shapes of facial landmarks. A linear layer with identity activations explicitly encodes landmark correlations by low-rank learning via matrix elastic nets. HORNet is highly flexible and can work either with pre-built feature representations or with convolutional architectures for end-to-end learning. HORNet leverages the strengths of both kernel methods in modeling nonlinearities and of neural networks in structural prediction. This combination renders it effective and efficient for direct face alignment. Extensive experiments on five in-the-wild datasets show that HORNet delivers high performance and consistently exceeds state-of-the-art methods.
DOI: 10.1198/tech.2003.s770
发表时间: 2003-08
期刊: Technometrics
影响因子: 2.5
作者:
E. Ziegel
通讯作者: E. Ziegel
DOI: 10.2140/pjm.1966.16.1
发表时间: 1966-01-01
影响因子: 0.6
作者:
ARMIJO, L
通讯作者: ARMIJO, L
DOI: --
发表时间: 2016-02
期刊: --
影响因子: --
作者:
Matus Telgarsky
通讯作者: Matus Telgarsky
DOI: --
发表时间: 2018
期刊: --
影响因子: --
作者:
Lei Yue;Xin Miao;Pengbo Wang;Baochang Zhang;Xiantong Zhen;Xianbin Cao
通讯作者: Lei Yue;Xin Miao;Pengbo Wang;Baochang Zhang;Xiantong Zhen;Xianbin Cao
DOI: 10.1007/978-3-319-46454-1_50
发表时间: 2015-11
期刊: ArXiv
影响因子: --
作者:
Oncel Tuzel;Tim K. Marks;S. Tambe
通讯作者: Oncel Tuzel;Tim K. Marks;S. Tambe