Deep Structured Prediction for Facial Landmark Detection

NeurIPS 2019  ·  Lisha Chen, Hui Su, Qiang Ji ·

Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric relationships between landmark points or generalize well to challenging conditions or unseen data. This paper proposes a method for deep structured facial landmark detection based on combining a deep Convolutional Network with a Conditional Random Field. We demonstrate its superior performance to existing state-of-the-art techniques in facial landmark detection, especially a better generalization ability on challenging datasets that include large pose and occlusion.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Facial Landmark Detection 300W CNN-CRF (Inter-ocular Norm) NME 3.30 # 6
Face Alignment 300W CNN-CRF NME_inter-ocular (%, Full) 3.30 # 22
NME_inter-ocular (%, Common) 2.93 # 24
NME_inter-ocular (%, Challenge) 4.84 # 14
NME_inter-pupil (%, Full) 4.63 # 14
NME_inter-pupil (%, Common) 4.06 # 15
NME_inter-pupil (%, Challenge) 6.98 # 10


No methods listed for this paper. Add relevant methods here