Multi-label learning based deep transfer neural network for facial attribute classification. (August 2018)

• Record Type: Journal Article
• Authors: Zhuang, Ni; Yan, Yan; Chen, Si; Wang, Hanzi; Shen, Chunhua
• Is Part Of: Pattern recognition. Volume 80(2018:Aug.)
• Page Start: 225
• Page End: 240
• Publication Date: 2018-08
• Subjects: Transfer learning -- Facial attribute classification -- Multi-label learning -- Deep learning -- Convolutional neural networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.03.018
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A deep transfer neural network, FMTNet, is proposed for facial attribute analysis. FMTNet effectively performs deep transfer learning based on multi-label learning. FMTNet has three sub-networks carefully designed in a similar network structure. An effective loss weight scheme is developed based on attribute grouping. Experiments on facial attribute analysis show the effectiveness of our method. Abstract: Deep Neural Network (DNN) has recently achieved outstanding performance in a variety of computer vision tasks, including facial attribute classification. The great success of classifying facial attributes with DNN often relies on a massive amount of labelled data. However, in real-world applications, labelled data are only provided for some commonly used attributes (such as age, gender); whereas, unlabelled data are available for other attributes (such as attraction, hairline). To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet). Firstly, based on the Faster Region-based Convolutional Neural Network (Faster R-CNN), FNet is fine-tuned for face detection. Then, MNet is fine-tuned by FNet to predict multiple attributes with labelled data, where an effective loss weight scheme is developed to explicitly exploit the correlation between facial attributes based on attribute grouping. Finally, based on MNet, TNet is trained by taking advantage of unsupervised domain adaptation for unlabelled facial attribute classification. The three sub-networks are tightly coupled to perform effective facial attribute classification. A distinguishing characteristic of the proposed FMTNet method is that the three sub-networks (FNet, MNet and TNet) are constructed in a similar network structure. Extensive experimental results on challenging face datasets demonstrate the effectiveness of our proposed method compared with several state-of-the-art methods.