Style Aggregated Network for Facial Landmark Detection

CVPR 2018 Xuanyi DongYan YanWanli OuyangYi Yang

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Facial Landmark Detection 300W SAN GT NME 3.98 # 2
Facial Landmark Detection AFLW-Front SAN Mean NME 1.85 # 1
Facial Landmark Detection AFLW-Full SAN Mean NME 1.91 # 1