Learning deep representation from coarse to fine for face alignment

2016/07/31 by Zhiwen Shao, Shouhong Ding, Shao, Zhiwen +7
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Speech and Audio Processing

paper · pdf · doi:10.48550/arxiv.1608.00207

openalex publication_date 2016/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a novel face alignment method that trains deep convolutional network from coarse to fine. It divides given landmarks into principal subset and elaborate subset. We firstly keep a large weight for principal subset to make our network primarily predict their locations while slightly take elaborate subset into account. Next the weight of principal subset is gradually decreased until two subsets have equivalent weights. This process contributes to learn a good initial model and search the optimal model smoothly to avoid missing fairly good intermediate models in subsequent procedures. On the challenging COFW dataset [1], our method achieves 6.33% mean error with a reduction of 21.37% compared with the best previous result [2].

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deeply learned face representations are sparse, selective, and robust

Related

• Deep Alignment Network: A convolutional neural network for robust face alignment
• Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression
• Effective face landmark localization via single deep network
• DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild
• Face Alignment by Local Deep Descriptor Regression