当前位置: X-MOL 学术Pattern Recogn. › 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.)
MobileFAN: Transferring Deep Hidden Representation for Face Alignment
Pattern Recognition ( IF 8 ) Pub Date : 2020-04-01 , DOI: 10.1016/j.patcog.2019.107114
Yang Zhao , Yifan Liu , Chunhua Shen , Yongsheng Gao , Shengwu Xiong

Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.

中文翻译:

MobileFAN:为人脸对齐传输深层隐藏表示

面部标志检测是许多面部分析应用程序的关键先决条件。基于深度学习的方法目前主导着解决面部标志检测的方法。然而,这样的作品通常会引入大量的参数,导致内存成本很高。在本文中,我们的目标是一种轻量级且有效的面部标志检测解决方案。为此,我们提出了一种有效的轻量级模型,即移动人脸对齐网络 (MobileFAN),使用简单的骨干网 MobileNetV2 作为编码器,使用三个反卷积层作为解码器。与最先进的模型相比,所提出的 MobileFAN 仅具有模型大小的 8% 和更低的计算成本,实现了卓越或相当的性能。而且,通过特征对齐蒸馏和特征相似蒸馏将人脸图的几何结构信息从大型复杂模型转移到我们提出的 MobileFAN,MobileFAN 的性能在人脸对齐的有效性和效率方面得到进一步提高。在三个具有挑战性的面部标志估计基准(包括 COFW、300W 和 WFLW)上的大量实验结果表明,我们提出的 MobileFAN 相对于最先进的方法具有优越性。
更新日期:2020-04-01
down
wechat
bug