Graph Jigsaw Learning for Cartoon Face Recognition

doi:10.1109/TIP.2022.3177952

	Graph Jigsaw Learning for Cartoon Face Recognition
	Li, Yong 1,2; Lao, Lingjie 1,2; Cui, Zhen 1,2; Shan, Shiguang 3,4,5; Yang, Jian 1,2
	2022
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	31 页码:3961-3972
摘要	Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognizing cartoon faces is to precisely perceive their sparse and critical shape patterns. However, it is quite difficult to learn a shape-oriented representation for cartoon face recognition with convolutional neural networks (CNNs). To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner. Solving the puzzles requires the model to spot the shape patterns of the cartoon faces as the texture information is quite limited. The key idea of GraphJigsaw is constructing a jigsaw puzzle by randomly shuffling the intermediate convolutional feature maps in the spatial dimension and exploiting the GCN to reason and recover the correct layout of the jigsaw fragments in a self-supervised manner. The proposed GraphJigsaw avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification. Specially, GraphJigsaw can be incorporated at various stages in a top-down manner within the classification model, which facilitates propagating the learned shape patterns gradually. GraphJigsaw does not rely on any extra manual annotation during the training process and incorporates no extra computation burden at inference time. Both quantitative and qualitative experimental results have verified the feasibility of our proposed GraphJigsaw, which consistently outperforms other face recognition or jigsaw-based methods on two popular cartoon face datasets with considerable improvements.
关键词	Face recognition Shape Training Image color analysis Layout Convolutional neural networks Task analysis Cartoon face recognition jigsaw solving graph convolutional network self-supervised learning
DOI	10.1109/TIP.2022.3177952
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0700800] ; National Natural Science Foundation of China[62102180] ; National Natural Science Foundation of China[62072244] ; Natural Science Foundation of Jiangsu Province[BK20210329] ; Fundamental Research Funds for the Central Universities[30921011104] ; Natural Science Foundation of Shandong Province[ZR2020LZH008] ; State Key Laboratory of High-End Server and Storage Technology
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000809404700007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19613
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cui, Zhen
作者单位	1.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, PCA Lab,Minist Educ, Key Lab Intelligent Percept & Syst High Dimens In, Nanjing 210094, Peoples R China 2.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Jiangsu Key Lab Image & Video Understanding Socia, Nanjing 210094, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 5.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Li, Yong,Lao, Lingjie,Cui, Zhen,et al. Graph Jigsaw Learning for Cartoon Face Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:3961-3972.
APA	Li, Yong,Lao, Lingjie,Cui, Zhen,Shan, Shiguang,&Yang, Jian.(2022).Graph Jigsaw Learning for Cartoon Face Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,3961-3972.
MLA	Li, Yong,et al."Graph Jigsaw Learning for Cartoon Face Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):3961-3972.