We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded sub-tasks: face bounding box refinement, general CSR and attention-controlled CSR. The first two stages refine initial face bounding boxes and output intermediate facial landmarks. Then, an online dynamic model selection method is used to choose appropriate domain-specific CSRs for further landmark refinement.

The proposed DAC-CSR has three stages in cascade: face bounding box refinement, general CSR and domain-specific CSR.
The three stages of DAC-CSR

The key innovation of our DAC-CSR is the fault-tolerant mechanism, using fuzzy set sample weighting for attention-controlled domain-specific model training. Moreover, we advocate data augmentation with a simple but effective 2D profile face generator, and context-aware feature extraction for better facial feature representation. Experimental results obtained on challenging datasets demonstrate the merits of our DAC-CSR over the state-of-the-art.


This paper was presented at CVPR 2017.

When: 22-25 July 2017
Where: Hawaii Convention Center
Honolulu, Hawaii


  • Full-text (3.52 Mb) – cite as:
    Z-H Feng, J Kittler, W Christmas, P Huber, X-J Wu, Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting, Proc. Conf. on Computer Vision and Pattern Recognition, 2017
Zhenhua Feng