Sub-pixel face landmarks using heatmaps and a bag of tricks
arXiv:2103.03059
Abstract
Accurate face landmark localization is an essential part of face recognition, reconstruction and morphing. To accurately localize face landmarks, we present our heatmap regression approach. Each model consists of a MobileNetV2 backbone followed by several upscaling layers, with different tricks to optimize both performance and inference cost. We use five naïve face landmarks from a publicly available face detector to position and align the face instead of using the bounding box like traditional methods. Moreover, we show by adding random rotation, displacement and scaling -- after alignment -- that the model is more sensitive to the face position than orientation. We also show that it is possible to reduce the upscaling complexity by using a mixture of deconvolution and pixel-shuffle layers without impeding localization performance. We present our state-of-the-art face landmark localization model (ranking second on The 2nd Grand Challenge of 106-Point Facial Landmark Localization validation set). Finally, we test the effect on face recognition using these landmarks, using a publicly available model and benchmarks.
arXiv comment10 pages, 1 figure
References in corpus (13)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- DeepPose: Human Pose Estimation via Deep Neural Networks
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Learning Deep Representation for Face Alignment with Auxiliary Attributes
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
- Partial FC: Training 10 Million Identities on a Single Machine
- AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
- Exploiting Facial Landmarks for Emotion Recognition in the Wild
- Face Detection with Feature Pyramids and Landmarks
- Grand Challenge of 106-Point Facial Landmark Localization
- Facial Action Unit Detection using 3D Facial Landmarks