当前位置: X-MOL 学术Comput. Vis. Image Underst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Small and accurate heatmap-based face alignment via distillation strategy and cascaded architecture
Computer Vision and Image Understanding ( IF 4.3 ) Pub Date : 2020-10-28 , DOI: 10.1016/j.cviu.2020.103125
Jiaxin Si , Fei Jiang , Ruimin Shen , Hongtao Lu

Despite face alignment has made significant progress, it is still challenging to get a small and accurate face landmark detection model. In this paper, we focus on compressing heatmap-based face alignment algorithms using a novel proposed distillation strategy. We find that the activated areas of heatmaps generated from the well-trained teacher net can capture more local shape information of the facial parts than the ground-truth ones generated from the standard Gaussian distribution. To simultaneously transfer such shape information and correct the mis-predicted heatmaps generated from the teacher model, we first modify the heatmaps of teacher model by replacing the mis-predicted heatmaps with the ground-truth ones as the labels for the student net. To further improve the accuracy of the student net, we investigate the correlation between the extracted features and the predicted heatmaps, and divide the landmarks into two categories: simple and hard. A cascaded architecture is designed which firstly detects the simple points based on the extracted features, and then predicts the hard points resorting to the heatmaps of simple ones. Finally, a face alignment model with 3.64M parameters is obtained, which is about 6x smaller than the cumbersome model, and outperforms the state-of-the-art algorithms on both AFLW2000-3D and 300W-LP. The model and code are released in https://github.com/snow-rgb/Fast-Face-Alignment.



中文翻译:

通过蒸馏策略和级联架构实现基于热图的小型,精确的面部对齐

尽管人脸对齐取得了长足的进步,但要获得一个小而准确的人脸标志检测模型仍然具有挑战性。在本文中,我们集中于使用一种新颖的提议蒸馏策略压缩基于热图的面部对齐算法。我们发现,受过良好训练的教师网络生成的热图激活区域比标准高斯分布生成的地面真实信息可以捕获更多的面部局部形状信息。为了同时传递这样的形状信息并纠正从教师模型生成的错误预测的热图,我们首先通过将错误预测的热图替换为地面真实的热图作为学生网络的标签来修改教师模型的热图。为了进一步提高学生网络的准确性,我们研究提取的特征与预测的热图之间的相关性,并将地标分为两类:简单和困难。设计了一个级联的体系结构,该体系结构首先基于提取的特征检测简单点,然后根据简单特征点的热图预测困难点。最终,获得了具有3.64M参数的面部对齐模型,该模型比笨拙的模型小大约6倍,并且在AFLW2000-3D和300W-LP上均优于最新算法。该模型和代码在https://github.com/snow-rgb/Fast-Face-Alignment中发布。然后预测诉诸于简单问题的热图的难点。最终,获得了具有3.64M参数的面部对齐模型,该模型比笨拙的模型小大约6倍,并且在AFLW2000-3D和300W-LP上均优于最新算法。该模型和代码在https://github.com/snow-rgb/Fast-Face-Alignment中发布。然后预测诉诸于简单问题的热图的难点。最终,获得了具有3.64M参数的面部对齐模型,该模型比笨拙的模型小大约6倍,并且在AFLW2000-3D和300W-LP上均优于最新算法。该模型和代码在https://github.com/snow-rgb/Fast-Face-Alignment中发布。

更新日期:2020-11-12
down
wechat
bug