Authors
Yue Wu*, Tal Hassner*, KangGeon Kim, Gerard Medioni, Prem Natarajan
Publication date
2018/12/1
Journal
IEEE transactions on pattern analysis and machine intelligence
Volume
40
Issue
12
Pages
3067-3074
Publisher
IEEE
Description
This paper concerns the problem of facial landmark detection. We provide a unique new analysis of the features produced at intermediate layers of a convolutional neural network (CNN) trained to regress facial landmark coordinates. This analysis shows that while being processed by the CNN, face images can be partitioned in an unsupervised manner into subsets containing faces in similar poses (i.e., 3D views) and facial properties (e.g., presence or absence of eye-wear). Based on this finding, we describe a novel CNN architecture, specialized to regress the facial landmark coordinates of faces in specific poses and appearances. To address the shortage of training data, particularly in extreme profile poses, we additionally present data augmentation techniques designed to provide sufficient training examples for each of these specialized sub-networks. The proposed Tweaked CNN (TCNN) architecture is shown …
Total citations
2016201720182019202020212022202320245112246373832289
Scholar articles
Y Wu, T Hassner, KG Kim, G Medioni, P Natarajan - IEEE transactions on pattern analysis and machine …, 2017