Convolutional Experts Constrained Local Model for Facial Landmark Detection

Amir Zadeh, Tadas Baltrusaitis, Louis-Philippe Morency; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 105-113

Constrained Local Models (CLMs) are a well- established family of methods for facial landmark detection. However, they have recently fallen out of favor to cascaded regression-based approaches. This is in part due to the inability of existing CLM local detectors to model the very complex individual landmark appearance that is affected by expression, illumination, facial hair, makeup, and accessories. In our work, we present a novel local detector - Convolutional Experts Network (CEN) - that brings together the advantages of neural architectures and mixtures of experts in an end-to-end framework. We further propose a Convolutional Experts Constrained Local Model (CE-CLM) algorithm that uses CEN as local detectors. We demonstrate that our proposed CE-CLM algorithm outperforms competitive state-of-the-art baselines for facial landmark detection by a large margin. Our approach is especially accurate and robust on challenging profile images.