模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2018, Vol. 31 Issue (12): 1085-1095    DOI: 10.16451/j.cnki.issn1003-6059.201812003
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Multistage Pedestrian Attribute Recognition Method Based on Improved Loss Function
ZHENG Shaofei1, TANG Jin1, LUO Bin1, WANG Xiao1, WANG Wenzhong1
1.School of Computer Science and Technology, Anhui University, Hefei 230601

Download: PDF (1023 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  There are plenty of studies on improving the performance of pedestrian attribute recognition in video surveillance scenarios by mining the positive correlations between attributes. However, the research on negative correlations is far from enough. In this paper, a deep learning based multi-stage pedestrian attribute recognition method is proposed to simultaneously explore the positive and negative correlations between attributes. In the first stage, the loss value and the accuracy of each attribute are calculated during training. In the second stage, a new network branch is designed for the attributes with larger average loss and lower average accuracy, while other attributes remain on the original branch. All attributes are predicted by these two branches jointly. In the third stage, two new network branches with same structure as the second stage are designed to optimize the parameters and improve the performance during attribute recognition. Moreover, an improved loss function increasing the distance between positive and negative samples is proposed, and it is applied in all training stages to further improve the performance. Experiments on datasets RAP and PETA validate the promising performance of the proposed method.
Key wordsVideo Surveillance      Pedestrian Attribute      Deep Learning      Multistage      Loss Function     
Received: 15 September 2018     
ZTFLH: TP 391.4  
Fund:Supported by National Natural Science Foundation of China(No.61671018,61472002,61502006)
About author:: (ZHENG Shaofei, master student. His research interests include computer vision and machine learning.)
(TANG Jin(Corresponding author), Ph.D., professor. His research interests include computer vision and big data processing.)
(LUO Bin, Ph.D., professor. His research interests include pattern recognition and graph matching theory.)
(WANG Xiao, Ph.D. candidate. His research interests include computer vision and pattern recognition.)
(WANG Wenzhong, Ph.D., lecturer. His research interests include computer vision and machine learning.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHENG Shaofei
TANG Jin
LUO Bin
WANG Xiao
WANG Wenzhong
Cite this article:   
ZHENG Shaofei,TANG Jin,LUO Bin等. Multistage Pedestrian Attribute Recognition Method Based on Improved Loss Function[J]. , 2018, 31(12): 1085-1095.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201812003      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2018/V31/I12/1085
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn