论文标题
用图形网络保留面部标志
Shape Preserving Facial Landmarks with Graph Attention Networks
论文作者
论文摘要
最佳地标估计算法基于利用大型卷积神经网络（CNN）的出色能力代表局部外观。但是，众所周知，他们只能学习薄弱的空间关系。为了解决这个问题，我们提出了一个基于CNN与图形注意网络回归层的组合的模型。为此，我们介绍了一个编码，该编码代表面部地标的外观和位置以及根据其可靠性权衡信息的注意机制。这与多任务的方法结合使用，以初始化图形节点的位置和粗到1的地标描述方案。我们的实验证实，所提出的模型了解了面部结构的全球表示，在头部姿势和地标估计的流行基准中实现了最高的性能。在我们的模型中提供的改进在涉及地标本地外观的情况下最为重要。
Top-performing landmark estimation algorithms are based on exploiting the excellent ability of large convolutional neural networks (CNNs) to represent local appearance. However, it is well known that they can only learn weak spatial relationships. To address this problem, we propose a model based on the combination of a CNN with a cascade of Graph Attention Network regressors. To this end, we introduce an encoding that jointly represents the appearance and location of facial landmarks and an attention mechanism to weigh the information according to its reliability. This is combined with a multi-task approach to initialize the location of graph nodes and a coarse-to-fine landmark description scheme. Our experiments confirm that the proposed model learns a global representation of the structure of the face, achieving top performance in popular benchmarks on head pose and landmark estimation. The improvement provided by our model is most significant in situations involving large changes in the local appearance of landmarks.
