More Web Proxy on the site http://driver.im/

research-article

Multi-Task Learning with Deep Dual-Path Network for Facial Attribute Recognition

Authors:

Shunzhi ZhuAuthors Info & Claims

ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

Pages 161 - 167

https://doi.org/10.1145/3436369.3437403

Published: 11 January 2021 Publication History

Abstract

Facial attribute recognition is a popular and challenging research topic in computer vision. In the traditional deep learning based attribute recognition methods, the mid-level network features and the differences between attribute groups are not fully explored. To solve the above problem, a deep dual-path network is proposed for facial attribute recognition. In the multi-task learning framework, two sub-networks are employed to respectively extract the features of two attribute groups, i.e., local attributes and global ones, and designed with both different scale images and different depth networks. Furthermore, an adaptive Focal loss penalty scheme is developed to automatically assign weights to handle the class imbalance problem for facial attribute recognition. Experimental results on the challenging CelebA dataset show that the proposed method achieves the better performance than state-of-the-art methods.

References

[1]

Kumar N, Berg A C, Belhumeur P N, Nayar S K. Describable visual attributes for face verification and image search, IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(10): 1962--1977.

Digital Library

[2]

Ganesh G P, Rohitash K B. A dynamic unconstrained feature matching algorithm for face recognition. Journal of Advances in Information Technology, 2020, 11(2): 103--108.

[3]

Qi G J, Aggarwal C, Tian Q, Ji H, Huang T. Exploring context and content links in social media: A latent space Method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(5): 850--862.

Digital Library

[4]

Qi G, Hua X, Zhang H. Learning semantic distance from community-tagged media collection. Proceedings of the 17th ACM international conference on Multimedia, 2009, pp. 243--252.

Digital Library

[5]

Ding H, Zhou H, Zhou S K, Chellappa R. A deep cascade network for unaligned face attribute classification. Proceedings of the 32ed AAAI Conference on Artificial Intelligence. 2018, pp. 6789--6796.

[6]

Zhang N, Paluri M, Ranzato M, Darrell T, Bourdev L. Panda: Pose aligned networks for deep attribute modeling. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014, pp. 1637--1644.

Digital Library

[7]

Rudd E M, Günther M, Boult T E. Moon: A mixed objective optimization network for the recognition of facial attributes. Proceedings of the European Conference on Computer Vision. 2016, pp. 19--35.

[8]

Han H, Jain A K, Shan S, Chen X. Heterogeneous face attribute estimation: A deep multi-task learning approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40: 2597--2609.

Digital Library

[9]

Collobert R, Weston J. A unified architecture for natural language processing: deep neural networks with multitask learning.Proceedings of the 25th international conference on Machine learning. 2008, pp. 160--167.

[10]

Caruana R. Multitask Learning. A knowledge based source of inductive bias. Proceedings of the 25th international conference on Machine learning. 1993, pp. 41--48.

[11]

Zhong Y, Sullivan J, Li H. Transferring from face recognition to face attribute prediction through adaptive selection of off-the-shelf cnn representations. In International Conference on Pattern Recognition, 2017, pp. 2264--2269.

[12]

Ijima T. Basic theory of pattern normalization (for the case of a typical one dimensional pattern). Bulletin of the Electrotechnical Laboratory. 1962, 26: 368--388.

[13]

Lin T Y, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2380--7504.

[14]

Kumar N, Berg A C, Belhumeur P. N, Nayar S. K. Attribute and simile classifiers for face verification. IEEE International Conference on Computer Vision. 2009, pp. 365--372.

[15]

Zhang N, Paluri M, Ranzato M, Darrell T, Bourdev L. Panda: Pose aligned networks for deep attribute modeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014, pp. 1637--1644.

Digital Library

[16]

Zhong Y, Sullivan J, Li H. Leveraging mid-level deep representations for predicting face attributes in the wild. Proceedings of IEEE International Conference on Image Processing. 2016, pp. 3239--3243.

[17]

Sharma A, Foroosh H. Slim-CNN: A light-weight CNN for face attribute prediction. arXiv:1907.02157. 2019.

[18]

Caruana R. Multitask learning. Machine Learning. 1997, pp. 41--75.

Digital Library

[19]

Zhang T, Ghanem B, Liu S, Ahuja N. Robust visual tracking via structured multi-task sparse learning. International Journal of Computer Vision. 2013, 367--383.

[20]

Zhou Q, Wang G, Jia K, Zhao Q. Learning to share latent tasks for action recognition. Proceedings of the IEEE International Conference on Computer Vision. 2013, pp. 2264--2271.

Digital Library

[21]

Rudd E M, Günther M, Boult T E. Moon: A mixed objective optimization network for the recognition of facial attributes. Proceedings of the European Conference on Computer Vision. 2016, pp. 19--35.

[22]

Sun Y, Yu J. General-to-specific learning for facial attribute classification in the wild. Journal of Visual Communication and Image Representation, 2018, 56: 83--91.

Digital Library

[23]

Hand E M, Chellappa R. Attributes for improved attributes: a multi-task network utilizing implicit and explicit relationships for facial attribute classification. Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco. 2017, pp. 4068--4074.

[24]

Cao J, Li Y, Zhang Z. Partially shared multi-task convolutional neural network with local constraint for face attribute learning. Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, pp. 4290--4299.

[25]

Han H, Jain A K, Shan S, Chen X. Heterogeneous face attribute estimation: A deep multi-task learning approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40: 2597--2609.

Digital Library

[26]

Fanhe X, Guo J, Huang Z, Qiu W, Zhang Y. Multi-Task learning with knowledge transfer for facial attribute classification. Proceedings of IEEE International Conference on Industrial Technology. 2019, pp. 877--882.

[27]

Liu Z, Luo P, Wang X, Tang X. Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision. 2015, pp. 3730--3738.

Digital Library

[28]

Evgin G. Analysis of Deep Networks with Residual Blocks and Different Activation Functions: Classification of Skin Diseases. Proceedings of the 2019 Ninth International Conference on Image Processing Theory, Tools and Applications. 2019, pp. 1--6.

[29]

Gao D, Yuan P, Sun N, Wu X, Cai Y. Face attribute prediction with convolutional neural networks. Proceedings of the IEEE International Conference on Robotics and Biomimetics. 2017, pp.1294--1299.

[30]

Wang J, Cheng Y, Schmidt Feris R. Walk and learn: Facial attribute representation learning from egocentric video and contextual data. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016, pp. 2295--2304.

[31]

Yip C, Hu H. Grouped multi-task CNN for facial attribute recognition. Proceedings of the 24th International Conference on Pattern Recognition. 2018, pp. 272--277.

[32]

Sethi A, Singh M, Singh R, Vatsa M. Residual codean autoencoder for facial attribute analysis. Pattern Recognition Letters. 2018, 119: 157--165.

Digital Library

Cited By

Liu NZhang FChang LDuan F(2023)Facial attribute classification by deep mining inter‐attribute correlationsIET Computer Vision10.1049/cvi2.12171Online publication date: 9-Jan-2023
https://doi.org/10.1049/cvi2.12171
Chen SLai XYan YWang DZhu S(2023)Learning an attention-aware parallel sharing network for facial attribute recognitionJournal of Visual Communication and Image Representation10.1016/j.jvcir.2022.10374590(103745)Online publication date: Feb-2023
https://doi.org/10.1016/j.jvcir.2022.103745
Liu NZhang FChang LDuan F(2023)Scattering-based hybrid network for facial attribute classificationFrontiers of Computer Science10.1007/s11704-023-2570-618:3Online publication date: 25-Nov-2023
https://doi.org/10.1007/s11704-023-2570-6

Index Terms

Multi-Task Learning with Deep Dual-Path Network for Facial Attribute Recognition
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Biometrics

Recommendations

Recognition of Facial Attributes Using Multi-Task Learning of Deep Networks
ICMLC '17: Proceedings of the 9th International Conference on Machine Learning and Computing

Face recognition is one of important topics in pattern recognition field. Besides recognizing personal identity, there have been numerous studies on recognizing various facial attributes such as gender, age, race, and expression. Recently, rapid growth ...
Multi-Task Pose-Invariant Face Recognition
Face images captured in unconstrained environments usually contain significant pose variation, which dramatically degrades the performance of algorithms designed to recognize frontal faces. This paper proposes a novel face identification framework capable ...
Learning an attention-aware parallel sharing network for facial attribute recognition
Abstract
Existing multi-task learning based facial attribute recognition (FAR) methods usually employ the serial sharing network, where the high-level global features are used for attribute prediction. However, the shared low-level features ...
Highlights
- An attention-aware parallel sharing network is proposed for attribute recognition.

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

October 2020

552 pages

ISBN:9781450387835

DOI:10.1145/3436369

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Beijing University of Technology

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 January 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Natural Science Foundation of Fujian Province of China
Joint Founds of Scientific and Technological Innovation Program of Fujian Province
Natural Science Foundation of China
Joint Funds of 5th Round of Health and Education Research Program of Fuijian Province

Conference

ICCPR 2020

ICCPR 2020: 2020 9th International Conference on Computing and Pattern Recognition

October 30 - November 1, 2020

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
194
Total Downloads

Downloads (Last 12 months)15
Downloads (Last 6 weeks)1

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Liu NZhang FChang LDuan F(2023)Facial attribute classification by deep mining inter‐attribute correlationsIET Computer Vision10.1049/cvi2.12171Online publication date: 9-Jan-2023
https://doi.org/10.1049/cvi2.12171
Chen SLai XYan YWang DZhu S(2023)Learning an attention-aware parallel sharing network for facial attribute recognitionJournal of Visual Communication and Image Representation10.1016/j.jvcir.2022.10374590(103745)Online publication date: Feb-2023
https://doi.org/10.1016/j.jvcir.2022.103745
Liu NZhang FChang LDuan F(2023)Scattering-based hybrid network for facial attribute classificationFrontiers of Computer Science10.1007/s11704-023-2570-618:3Online publication date: 25-Nov-2023
https://doi.org/10.1007/s11704-023-2570-6

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents