Abstract 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.

中文翻译：

---

用于直接人脸对齐的异构输出回归网络

摘要 人脸对齐由于其广泛的应用在计算机视觉中获得了极大的普及。在本文中，我们提出了一种新的学习架构，即异构输出回归网络（HORNet），用于面部对齐，它直接从图像中预测面部标志。HORNet 基于核近似，建立了一个新的紧凑的多层架构。具有余弦激活的非线性层解开图像表示和面部标志形状之间的非线性关系。具有身份激活的线性层通过矩阵弹性网络通过低秩学习显式编码地标相关性。HORNet 非常灵活，可以使用预先构建的特征表示或卷积架构进行端到端学习。HORNet 利用内核方法在非线性建模和神经网络在结构预测方面的优势。这种组合使其对于直接面部对齐有效且高效。对五个野外数据集进行的大量实验表明，HORNet 具有高性能，并且始终超过最先进的方法。