Facial Landmark Detection with Tweaked Convolutional Neural Networks
arXiv:1511.04031
Abstract
We present a novel convolutional neural network (CNN) design for facial landmark coordinate regression. We examine the intermediate features of a standard CNN trained for landmark detection and show that features extracted from later, more specialized layers capture rough landmark locations. This provides a natural means of applying differential treatment midway through the network, tweaking processing based on facial alignment. The resulting Tweaked CNN model (TCNN) harnesses the robustness of CNNs for landmark detection, in an appearance-sensitive manner without training multi-part or multi-scale models. Our results on standard face landmark detection and face verification benchmarks show TCNN to surpasses previously published performances by wide margins.
First two authors had joint first authorship / equal contribution
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Face Representation from Scratch
- DRAW: A Recurrent Neural Network For Image Generation
- Learning Deep Representation for Face Alignment with Auxiliary Attributes
- Unconstrained Facial Landmark Localization with Backbone-Branches Fully-Convolutional Networks
- Understanding deep features with computer-generated imagery
- Mirror, mirror on the wall, tell me, is the error small?
Cited by in corpus (8)
- Face Alignment Across Large Poses: A 3D Solution
- Face Alignment in Full Pose Range: A 3D Total Solution
- Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
- FacePoseNet: Making a Case for Landmark-Free Face Alignment
- Multi-Objective Convolutional Neural Networks for Robot Localisation and 3D Position Estimation in 2D Camera Images
- Face Synthesis with Landmark Points from Generative Adversarial Networks and Inverse Latent Space Mapping
- Interspecies Knowledge Transfer for Facial Keypoint Detection
- Visual Data Augmentation through Learning