论文标题
高斯矢量：面部地标检测的有效解决方案
Gaussian Vector: An Efficient Solution for Facial Landmark Detection
论文作者
论文摘要
随着卷积神经网络的发展，面部地标检测取得了重大进展。广泛使用的算法可以分类为坐标回归方法和基于热图的方法。但是，前者丢失了空间信息，导致性能差，而后者遭受了较大的输出尺寸或高后处理的复杂性。本文提出了一种新的解决方案高斯矢量，以保留空间信息，并减少输出尺寸并简化后处理。我们的方法提供了新颖的矢量监督，并引入了带池模块，以将热图转换为每个地标的一对矢量。这是一个简单有效的插件组件。此外，提出了超越盒子策略来处理面部边界框的地标。我们在300W，COFW，WFLW和JD-Landmark上评估我们的方法。结果显着超过了先前的作品，证明了我们方法的有效性。
Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate regression methods and heatmap based methods. However, the former loses spatial information, resulting in poor performance while the latter suffers from large output size or high post-processing complexity. This paper proposes a new solution, Gaussian Vector, to preserve the spatial information as well as reduce the output size and simplify the post-processing. Our method provides novel vector supervision and introduces Band Pooling Module to convert heatmap into a pair of vectors for each landmark. This is a plug-and-play component which is simple and effective. Moreover, Beyond Box Strategy is proposed to handle the landmarks out of the face bounding box. We evaluate our method on 300W, COFW, WFLW and JD-landmark. That the results significantly surpass previous works demonstrates the effectiveness of our approach.
