Fine-Grained Face Annotation Using Deep Multi-Task CNN
Open Access
Abstract
We present a multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously. In total, the model is able to estimate up to 74 different face attributes belonging to three distinct recognition tasks: age group, gender and visual attributes (such as hair color, face shape and the presence of makeup). The proposed model shares all the CNN’s parameters among tasks and deals with task-specific estimation through the introduction of two components: (i) a gating mechanism to control activations’ sharing and to adaptively route them across different face attributes; (ii) a module to post-process the predictions in order to take into account the correlation among face attributes. The model is trained by fusing multiple databases for increasing the number of face attributes that can be estimated and using a center loss for disentangling representations among face attributes in the embedding space. Extensive experiments validate the effectiveness of the proposed approach.Keywords
This publication has 26 references indexed in Scilit:
- Robust smile detection using convolutional neural networksJournal of Electronic Imaging, 2016
- MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes2016
- A Discriminative Feature Learning Approach for Deep Face Recognition2016
- Deep Expectation of Real and Apparent Age from a Single Image Without Facial LandmarksInternational Journal of Computer Vision, 2016
- Deep Learning Face Attributes in the Wild2015
- Deep Convolutional Neural Networks and Support Vector Machines for Gender Recognition2015
- Effective face frontalization in unconstrained images2015
- Age and Gender Estimation of Unfiltered FacesIEEE Transactions on Information Forensics and Security, 2014
- PANDA: Pose Aligned Networks for Deep Attribute Modeling2014
- Long Short-Term MemoryNeural Computation, 1997