中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition

文献类型：期刊论文

作者Yang, Yang1,2; Tan, Zichang4,5; Tiwari, Prayag6; Pandey, Hari Mohan7; Wan, Jun1,2; Lei, Zhen1,2,3; Guo, Guodong4,5; Li, Stan Z.1
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2021-07-18
页码14
关键词Pedestrian attribute recognition Attention Split-and-aggregate learning Feature recombination
ISSN号0920-5691
DOI10.1007/s11263-021-01499-z
通讯作者Wan, Jun(jun.wan@nlpr.ia.ac.cn)
英文摘要Multi-label pedestrian attribute recognition in surveillance is inherently a challenging task due to poor imaging quality, large pose variations, and so on. In this paper, we improve its performance from the following two aspects: (1) We propose a cascaded Split-and-Aggregate Learning (SAL) to capture both the individuality and commonality for all attributes, with one at the feature map level and the other at the feature vector level. For the former, we split the features of each attribute by using a designed attribute-specific attention module (ASAM). For the later, the split features for each attribute are learned by using constrained losses. In both modules, the split features are aggregated by using several convolutional or fully connected layers. (2) We propose a Feature Recombination (FR) that conducts a random shuffle based on the split features over a batch of samples to synthesize more training samples, which spans the potential samples' variability. To the end, we formulate a unified framework, named CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR), to learn the above modules jointly and concurrently. Experiments on five popular benchmarks, including RAP, PA-100K, PETA, Market-1501 and Duke attribute datasets, show the proposed CAS-SAL-FR achieves new state-of-the-art performance.
资助项目National Key Research and Development Program[2020YFC2003901] ; Chinese National Natural Science Foundation[61806203] ; Chinese National Natural Science Foundation[61961160704] ; Chinese National Natural Science Foundation[61876179] ; External cooperation key project of Chinese Academy Sciences[173211KYSB20200002] ; Key Project of the General Logistics Department[AWS17J001] ; Science and Technology Development Fund of Macau[0010/2019/AFJ] ; Science and Technology Development Fund of Macau[0025/2019/AKP] ; Science and Technology Development Fund of Macau[0019/2018/ASC] ; Spanish project (MINECO/FEDER, UE)[TIN2016-74946-P] ; CERCA Programme/Generalitat de Catalunya ; Academy of Finland[336033] ; Academy of Finland[315896] ; Business Finland[884/31/2018] ; EU[101016775]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000674202900001
出版者SPRINGER
资助机构National Key Research and Development Program ; Chinese National Natural Science Foundation ; External cooperation key project of Chinese Academy Sciences ; Key Project of the General Logistics Department ; Science and Technology Development Fund of Macau ; Spanish project (MINECO/FEDER, UE) ; CERCA Programme/Generalitat de Catalunya ; Academy of Finland ; Business Finland ; EU
源URL[http://ir.ia.ac.cn/handle/173211/45511]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者Wan, Jun
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Biometr & Secur Res, Beijing, Peoples R China
2.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing, Peoples R China
3.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China
4.Baidu Res, Inst Deep Learning, Beijing, Peoples R China
5.Natl Engn Lab Deep Learning Technol & Applicat, Beijing, Peoples R China
6.Aalto Univ, Dept Comp Sci, Espoo, Finland
7.Edge Hill Univ, Dept Comp Sci, Ormskirk, England
推荐引用方式
GB/T 7714		 Yang, Yang,Tan, Zichang,Tiwari, Prayag,et al. Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2021:14.
APA Yang, Yang.,Tan, Zichang.,Tiwari, Prayag.,Pandey, Hari Mohan.,Wan, Jun.,...&Li, Stan Z..(2021).Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition.INTERNATIONAL JOURNAL OF COMPUTER VISION,14.
MLA Yang, Yang,et al."Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition".INTERNATIONAL JOURNAL OF COMPUTER VISION (2021):14.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。