Gaussian Vector: An Efficient Solution for Facial Landmark Detection
arXiv:2010.01318
Abstract
Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate regression methods and heatmap based methods. However, the former loses spatial information, resulting in poor performance while the latter suffers from large output size or high post-processing complexity. This paper proposes a new solution, Gaussian Vector, to preserve the spatial information as well as reduce the output size and simplify the post-processing. Our method provides novel vector supervision and introduces Band Pooling Module to convert heatmap into a pair of vectors for each landmark. This is a plug-and-play component which is simple and effective. Moreover, Beyond Box Strategy is proposed to handle the landmarks out of the face bounding box. We evaluate our method on 300W, COFW, WFLW and JD-landmark. That the results significantly surpass previous works demonstrates the effectiveness of our approach.
arXiv comment19 pages, 8 figures
References in corpus (9)
- Fully Convolutional Networks for Semantic Segmentation
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- End-to-End Training of Deep Visuomotor Policies
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- High-Resolution Representations for Labeling Pixels and Regions
- Face Alignment Across Large Poses: A 3D Solution
- Face Alignment in Full Pose Range: A 3D Total Solution
- Numerical Coordinate Regression with Convolutional Neural Networks
- Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks