Facial Landmark Detection with Tweaked Convolutional Neural Networks
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.
Cite
@article{arxiv.1511.04031,
title = {Facial Landmark Detection with Tweaked Convolutional Neural Networks},
author = {Yue Wu and Tal Hassner and KangGeon Kim and Gerard Medioni and Prem Natarajan},
journal= {arXiv preprint arXiv:1511.04031},
year = {2016}
}
Comments
First two authors had joint first authorship / equal contribution