Facial Landmarks Detection by Self-Iterative Regression based Landmarks-Attention Network

18 Mar 2018  ·  Tao Hu, Honggang Qi, Jizheng Xu, Qingming Huang ·

Cascaded Regression (CR) based methods have been proposed to solve facial landmarks detection problem, which learn a series of descent directions by multiple cascaded regressors separately trained in coarse and fine stages. They outperform the traditional gradient descent based methods in both accuracy and running speed. However, cascaded regression is not robust enough because each regressor's training data comes from the output of previous regressor. Moreover, training multiple regressors requires lots of computing resources, especially for deep learning based methods. In this paper, we develop a Self-Iterative Regression (SIR) framework to improve the model efficiency. Only one self-iterative regressor is trained to learn the descent directions for samples from coarse stages to fine stages, and parameters are iteratively updated by the same regressor. Specifically, we proposed Landmarks-Attention Network (LAN) as our regressor, which concurrently learns features around each landmark and obtains the holistic location increment. By doing so, not only the rest of regressors are removed to simplify the training process, but the number of model parameters is significantly decreased. The experiments demonstrate that with only 3.72M model parameters, our proposed method achieves the state-of-the-art performance.

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper

Ranked #16 on Face Alignment on 300W (NME_inter-pupil (%, Common) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Alignment 300W SIR-LAN NME_inter-pupil (%, Full) 5.04 # 17
NME_inter-pupil (%, Common) 4.29 # 16
NME_inter-pupil (%, Challenge) 8.14 # 17


No methods listed for this paper. Add relevant methods here