Facial landmark detection aims at localizing multiple keypoints for a given facial image, which usually suffers from variations caused by arbitrary pose, diverse facial expression and partial occlusion. In this paper, we develop a two-stage regression network for facial landmark detection on unconstrained conditions. Our model consists of a Structural Hourglass Network (SHN) for detecting the initial locations of all facial landmarks based on heatmap generation, and a Global Constraint Network (GCN) for further refining the detected locations based on offset estimation. Specifically, SHN introduces an improved Inception-ResNet unit as basic building block, which can effectively improve the receptive field and learn contextual feature representations. In the meanwhile, a novel loss function with adaptive weight is proposed to make the whole model focus on the hard landmarks precisely. GCN attempts to explore the spatial contextual relationship between facial landmarks and refine the initial locations of facial landmarks by optimizing the global constraint. Moreover, we develop a pre-processing network to generate features with different scales, which will be transmitted to SHN and GCN for effective feature representations. Different from existing models, the proposed method realizes the heatmap-offset framework, which combines the outputs of heatmaps generated by SHN and coordinates estimated by GCN, to obtain an accurate prediction. The extensive experimental results on several challenging datasets, including 300W, COFW, AFLW, and 300-VW confirm that our method achieve competitive performance compared with the state-of-the-art algorithms.

中文翻译：

---

通过热图偏移回归进行稳健的面部标志检测


面部标志检测旨在定位给定面部图像的多个关键点，该图像通常会受到任意姿势、不同面部表情和部分遮挡引起的变化的影响。在本文中，我们开发了一个两阶段回归网络，用于在无约束条件下进行面部标志检测。我们的模型由结构沙漏网络（SHN）和全局约束网络（GCN）组成，结构沙漏网络（SHN）用于基于热图生成检测所有面部标志的初始位置，全局约束网络（GCN）用于基于偏移估计进一步细化检测到的位置。具体来说，SHN 引入了改进的 Inception-ResNet 单元作为基本构建块，可以有效改善感受野并学习上下文特征表示。同时，提出了一种具有自适应权重的新型损失函数，使整个模型精确地聚焦于硬地标。 GCN尝试探索面部标志点之间的空间上下文关系，并通过优化全局约束来细化面部标志点的初始位置。此外，我们开发了一个预处理网络来生成不同尺度的特征，这些特征将被传输到 SHN 和 GCN 进行有效的特征表示。与现有模型不同，该方法实现了热图偏移框架，该框架结合了SHN生成的热图的输出和GCN估计的坐标，以获得准确的预测。在几个具有挑战性的数据集（包括 300W、COFW、AFLW 和 300-VW）上进行的广泛实验结果证实，与最先进的算法相比，我们的方法实现了具有竞争力的性能。