Deep Structured Prediction for Facial Landmark Detection
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
300W
COFW
| 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 |
Methods
No methods listed for this paper. Add
relevant methods here
