research-article

Adaptively Weighted Multi-task Deep Network for Person Attribute Classification

Authors:

Zhanxiong Wang,

Xiangyang XueAuthors Info & Claims

MM '17: Proceedings of the 25th ACM international conference on Multimedia

Pages 1636 - 1644

https://doi.org/10.1145/3123266.3123424

Published: 23 October 2017 Publication History

Abstract

Multi-task learning aims to boost the performance of multiple prediction tasks by appropriately sharing relevant information among them. However, it always suffers from the negative transfer problem. And due to the diverse learning difficulties and convergence rates of different tasks, jointly optimizing multiple tasks is very challenging. To solve these problems, we present a weighted multi-task deep convolutional neural network for person attribute analysis. A novel validation loss trend algorithm is, for the first time proposed to dynamically and adaptively update the weight for learning each task in the training process. Extensive experiments on CelebA, Market-1501 attribute and Duke attribute datasets clearly show that state-of-the-art performance is obtained; and this validates the effectiveness of our proposed framework.

References

[1]

Abrar H Abdulnabi, Gang Wang, Jiwen Lu, and Kui Jia. 2015. Multi-task cnn model for attribute prediction. IEEE TMM (2015).

Digital Library

[2]

Anna Bosch, Andrew Zisserman, and Xavier Munoz. 2007. Representing shape with a spatial pyramid kernel. ACM International Conference on Image and Video Retrieval.

Digital Library

[3]

Rich Caruana. 1998. Multitask learning. Learning to learn. Springer, 95--133.

Digital Library

[4]

Yubin Deng, Ping Luo, Chen Change Loy, and Xiaoou Tang. 2014. Pedestrian Attribute Recognition At Far Distance. ACM MM.

Digital Library

[5]

Simon Denman, Clinton Fookes, Alina Bialkowski, and Sridha Sridharan. 2009. Soft-biometrics: Unconstrained Authentication in a Surveillance Environment Digital Image Computing: Techniques and Applications.

Digital Library

[6]

Max Ehrlich, Timothy J Shields, Timur Almaev, and Mohamed R Amer. 2016. Facial attributes classification using multi-task representation learning CVPR Workshops.

[7]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015).

[8]

J. Huang, R. S. Feris, Q. Chen, and S. Yan. 2015. Cross-domain image retrieval with a dual attribute-aware ranking network ICCV.

Digital Library

[9]

Rabia Jafri and Hamid R. Arabnia. 2009. A Survey of Face Recognition Techniques. In Journal of Information Processing Systems.

[10]

Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Gir-shick, S. Guadarrama, and T. Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. arXiv (2014).

Digital Library

[11]

B. Jou and S.F. Chang. 2016 a. Deep cross residual learning for multi-task visual recognition ACM MM.

Digital Library

[12]

Brendan Jou and Shih-Fu Chang. 2016 b. Deep Cross Residual Learning for Multitask Visual Recognition Proceedings of the 2016 ACM on Multimedia Conference. ACM, 998--1007.

Digital Library

[13]

Neeraj Kumar, Peter Belhumeur, and Shree Nayar. 2008. Facetracer: A search engine for large collections of images with faces European conference on computer vision. Springer, 340--353.

Digital Library

[14]

Neeraj Kumar, Alexander Berg, Peter N Belhumeur, and Shree Nayar. 2011. Describable visual attributes for face verification and image search. IEEE TPMAI (2011).

Digital Library

[15]

Neeraj Kumar, Alexander C Berg, Peter N Belhumeur, and Shree K Nayar. 2009. Attribute and simile classifiers for face verification ICCV. IEEE, 365--372.

[16]

Giwoong Lee, Eunho Yang, and Sung Ju Hwang. 2016. Asymmetric Multi-task Learning Based on Task Relatedness and Loss ICML.

Digital Library

[17]

Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, and Yi Yang. 2017. Improving Person Re-identification by Attribute and Identity Learning. arXiv preprint arXiv:1703.07220 (2017).

[18]

L. Liu, J. Xing, S. Liu, H. Xu, X. Zhou, and S. Yan. 2014. Wow! you are so beautiful today! ACM TMCCA (2014).

Digital Library

[19]

Xiaodong Liu, Jianfeng Gao, Xiaodong He, Li Deng, Kevin Duh, and Ye-Yi Wang. {n. d.}. Representation learning using multi-task deep neural networks for semantic classification and information retrieval.

[20]

Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. 2015. Deep learning face attributes in the wild. In ICCV.

Digital Library

[21]

Yongxi Lu, Abhishek Kumar, Shuangfei Zhai, Yu Cheng, Tara Javidi, and Rogerio Feris. 2017. Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification. In CVPR.

[22]

Sinno Jialin Pan and Qiang Yang. 2010. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, Vol. 22, 10 (2010), 1345--1359.

Digital Library

[23]

Rajeev Ranjan, Vishal M Patel, and Rama Chellappa. 2016 a. Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. arXiv preprint arXiv:1603.01249 (2016).

[24]

Rajeev Ranjan, Swami Sankaranarayanan, Carlos D. Castillo, and Rama Chellappa. 2016 b. An All-In-One Convolutional Neural Network for Face Analysis arxiv.

[25]

Ali Sharif Razavian, Josephine Sullivan, and Stefan Carlsson 2014. CNN Features off-the-shelf: an Astounding Baseline for Recognition. IEEE Conference on Computer Vision and Pattern Recognition'14 workshop on Deep vision (2014).

Digital Library

[26]

Ethan M. Rudd, Manuel Gunther, and Terrance E. Boult. 2016. MOON:A Mixed Objective Optimization Network for the Recognition of Facial Attributes ECCV.

[27]

Behjat Siddiquie, Rogerio Feris, and Larry Davis. 2011. Image Ranking and Retrieval Based on Multi-Attribute Queries IEEE Conference on Computer Vision and Pattern Recognition.

Digital Library

[28]

S. Thrun. 1996. Learning To Learn: Introduction. Kluwer Academic Publishers.

[29]

D.A. Vaquero, R.S. Feris, D. Tran, L. Brown, A. Hampapur, and M. Turk. 2009. Attribute-based people search in surveillance environments IEEE WACV.

Cited By

Lu WHu HYu JZhou YWang HLi B(2024)Orientation-Aware Pedestrian Attribute Recognition Based on Graph Convolution NetworkIEEE Transactions on Multimedia10.1109/TMM.2023.325968626(28-40)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3259686
Liu XWu BWei CYan X(2024)InverMulT-STP: Closed-Loop Transformer Seismic AVA Inversion With Synthetic Data Style Transfer PretrainingIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.340945062(1-18)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3409450
Yao SPan KWang TZheng ZJin JHu C(2024)AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-IdentificationIEEE Transactions on Consumer Electronics10.1109/TCE.2024.345389070:4(6580-6588)Online publication date: Nov-2024
https://doi.org/10.1109/TCE.2024.3453890
Show More Cited By

Adaptively Weighted Multi-task Deep Network for Person Attribute Classification
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches

Recommendations

Multi-task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval

Deep neural networks have significantly improved the performance of face recognition and facial attribute prediction, which however are still very challenging on the million scale dataset, i.e. MegaFace. In this paper, we for the first time, advocate a ...
Excluding the Misleading Relatedness Between Attributes in Multi-Task Attribute Recognition Network
MMAsia '19: Proceedings of the 1st ACM International Conference on Multimedia in Asia

In the attribute recognition area, attributes that are unrelated in the real world may have a high co-occurrence rate in a dataset due to the dataset bias, which forms a misleading relatedness. A neural network, especially a multi-task neural network, ...
Multi-task learning using a hybrid representation for text classification
Abstract
Text classification is an important task in machine learning. Specifically, deep neural network has been shown strong capability to improve performance in different fields, for example speech recognition, objects recognition and natural language ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '17: Proceedings of the 25th ACM international conference on Multimedia

October 2017

2028 pages

ISBN:9781450349062

DOI:10.1145/3123266

General Chairs:
Qiong Liu
FXPAL, USA
,
Rainer Lienhart
Universität Augsburg, Germany
,
Haohong Wang
TCL America, USA
,
Program Chairs:
Sheng-Wei "Kuan-Ta" Chen
Academia Sinica, Taiwan
,
Susanne Boll
University of Oldenburg, Germany
,
Phoebe Chen
La Trobe University, Australia
,
Gerald Friedland
Lawrence Livermore National Lab, USA
,
Jia Li
Google, USA
,
Shuicheng Yan
Qihoo 360, China

Copyright © 2017 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]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 23 October 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

MM '17

Sponsor:

SIGMM

MM '17: ACM Multimedia Conference

October 23 - 27, 2017

California, Mountain View, USA

Acceptance Rates

MM '17 Paper Acceptance Rate 189 of 684 submissions, 28%;

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

43
Total Citations
View Citations
823
Total Downloads

Downloads (Last 12 months)58
Downloads (Last 6 weeks)9

Reflects downloads up to 27 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Lu WHu HYu JZhou YWang HLi B(2024)Orientation-Aware Pedestrian Attribute Recognition Based on Graph Convolution NetworkIEEE Transactions on Multimedia10.1109/TMM.2023.325968626(28-40)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3259686
Liu XWu BWei CYan X(2024)InverMulT-STP: Closed-Loop Transformer Seismic AVA Inversion With Synthetic Data Style Transfer PretrainingIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.340945062(1-18)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3409450
Yao SPan KWang TZheng ZJin JHu C(2024)AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-IdentificationIEEE Transactions on Consumer Electronics10.1109/TCE.2024.345389070:4(6580-6588)Online publication date: Nov-2024
https://doi.org/10.1109/TCE.2024.3453890
Liu SWang HChen JLuo KFan J(2024)High-resolution reconstruction of turbulent flames from sparse data with physics-informed neural networksCombustion and Flame10.1016/j.combustflame.2023.113275260(113275)Online publication date: Feb-2024
https://doi.org/10.1016/j.combustflame.2023.113275
Lu WHu HYu JZhang SWang H(2023)Explicit State Representation Guided Video-based Pedestrian Attribute RecognitionACM Transactions on Intelligent Systems and Technology10.1145/362624015:1(1-24)Online publication date: 19-Dec-2023
https://dl.acm.org/doi/10.1145/3626240
Zhang YWang SKan SWeng ZCen YTan YEl Saddik AMei TCucchiara RBertini MTobon Vallejo DAtrey PHossain M(2023)POAR: Towards Open Vocabulary Pedestrian Attribute RecognitionProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3611719(655-665)Online publication date: 26-Oct-2023
https://dl.acm.org/doi/10.1145/3581783.3611719
Fang YCai SCao YLi ZZhang Z(2023)Adversarial Learning Guided Task Relatedness Refinement for Multi-Task Deep LearningIEEE Transactions on Multimedia10.1109/TMM.2022.321646025(6946-6957)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1109/TMM.2022.3216460
Wu JHuang YGao MGao ZZhao JShi JZhang A(2023)Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute RecognitionIEEE Transactions on Information Forensics and Security10.1109/TIFS.2023.331158418(5623-5635)Online publication date: 2023
https://doi.org/10.1109/TIFS.2023.3311584
Yan YXu YXue JLu YWang HZhu W(2023)Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled SamplesIEEE Transactions on Cybernetics10.1109/TCYB.2022.317335653:11(7071-7084)Online publication date: Nov-2023
https://doi.org/10.1109/TCYB.2022.3173356
Ravikiran MBiswas SGanesh A(2023)Hi-GoTE: Hierarchical Group-Wise Temporal Ensembling for Semi-Supervised Pedestrian Attribute Recognition2023 International Conference on Machine Learning and Applications (ICMLA)10.1109/ICMLA58977.2023.00172(1150-1155)Online publication date: 15-Dec-2023
https://doi.org/10.1109/ICMLA58977.2023.00172
Show More Cited By

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.

Figures

Tables

Media

View Table of Conten