Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition

doi:10.1109/TNNLS.2023.3333542

CSpace

	Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition
	Cai, Shaofei 1; Li, Liang 1; Han, Xinzhe 1,2; Huang, Shan 3; Tian, Qi 4; Huang, Qingming 1,2,5
	2023-11-30
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	13
摘要	Multilabel image recognition (MLR) aims to annotate an image with comprehensive labels and suffers from object occlusion or small object sizes within images. Although the existing works attempt to capture and exploit label correlations to tackle these issues, they predominantly rely on global statistical label correlations as prior knowledge for guiding label prediction, neglecting the unique label correlations present within each image. To overcome this limitation, we propose a semantic and correlation disentangled graph convolution (SCD-GC) method, which builds the image-specific graph and employs graph propagation to reason the labels effectively. Specifically, we introduce a semantic disentangling module to extract categorywise semantic features as graph nodes and develop a correlation disentangling module to extract image-specific label correlations as graph edges. Performing graph convolutions on this image-specific graph allows for better mining of difficult labels with weak visual representations. Visualization experiments reveal that our approach successfully disentangles the dominant label correlations existing within the input image. Through extensive experimentation, we demonstrate that our method achieves superior results on the challenging Microsoft COCO (MS-COCO), PASCAL visual object classes (PASCAL-VOC), NUS web image dataset (NUS-WIDE), and Visual Genome 500 (VG-500) datasets. Code is available at GitHub: https://github.com/caigitrepo/SCDGC.
关键词	Attention mechanism feature disentangling graph convolutional network (GCN) multilabel recognition
DOI	10.1109/TNNLS.2023.3333542
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001121688300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[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/2XEOYT63/38486
专题	中国科学院计算技术研究所
通讯作者	Li, Liang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100190, Peoples R China 3.Tencent, Beijing 100085, Peoples R China 4.Huawei Technol, Cloud BU, Shenzhen 100190, Peoples R China 5.Peng Cheng Lab, Shenzhen 518066, Peoples R China
推荐引用方式 GB/T 7714	Cai, Shaofei,Li, Liang,Han, Xinzhe,et al. Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:13.
APA	Cai, Shaofei,Li, Liang,Han, Xinzhe,Huang, Shan,Tian, Qi,&Huang, Qingming.(2023).Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA	Cai, Shaofei,et al."Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):13.