Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/119066
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Multi-label learning based deep transfer neural network for facial attribute classification |
Author: | Zhuang, N. Yan, Y. Chen, S. Wang, H. Shen, C. |
Citation: | Pattern Recognition, 2018; 80:225-240 |
Publisher: | Elsevier |
Issue Date: | 2018 |
ISSN: | 0031-3203 1873-5142 |
Statement of Responsibility: | Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang, Chunhua Shen |
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. |
Rights: | © 2018 Elsevier Ltd. All rights reserved. |
DOI: | 10.1016/j.patcog.2018.03.018 |
Grant ID: | 61571379 61503315 U1605252 61472334 |
Published version: | http://dx.doi.org/10.1016/j.patcog.2018.03.018 |
Appears in Collections: | Aurora harvest 8 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.