GAANet: Graph Aggregation Alignment Feature Fusion for Multispectral Object Detection

doi:10.1109/TII.2025.3588622

科研成果详情

题名	GAANet: Graph Aggregation Alignment Feature Fusion for Multispectral Object Detection
作者	Zheng，Zihao 1; Zhou，Mingliang 1; Shang，Zhaowei 1; Wei，Xuekai 1; Pu，Huayan 2; Luo，Jun 2; Jia，Weijia 3
发表日期	2025
发表期刊	IEEE Transactions on Industrial Informatics
ISSN/eISSN	1551-3203
摘要	Multispectral object detection has shown great promise in security and industrial applications. RGB images offer rich texture but are limited by lighting, whereas IR images excel in low light but lack texture. Current methods face challenges in accurately capturing information differences and achieving effective feature fusion across modalities. To address these issues, we propose a graph aggregation alignment network (GAANet) for multispectral object detection. GAANet consists of two key modules: the graph interaction fusion module (GIFM) and the information alignment module (IAM). GIFM uses graph representation learning to effectively process single-modality features, and the direct connection information flow mechanism guides and references low-level multimodal features, ensuring the global and comprehensive fusion of node information in the graph space. The results are then refined through the IAM for secondary calibration and alignment of corresponding local regions, ensuring accurate fusion. We also introduce an information reconstruction path (IRP) and reconstruction loss to prevent the loss of single-modality information due to multiple IAM calculations. GAANet achieves excellent fusion detection capability and significantly reduces the number of parameters, reducing the model size by 61.2% compared with that of representative baselines such as CALNet. GAANet achieves state-of-the-art results on the DroneVehicle, LLVIP, and FLIR datasets, with superior object detection accuracy. It also performs well on the unaligned DVTOD dataset, effectively capturing feature offsets across modalities through global graph perception.
关键词	Multimodal feature alignment multimodal fusion multispectral object detection
DOI	10.1109/TII.2025.3588622
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-105012118989
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13722
专题	北师香港浸会大学
通讯作者	Zhou，Mingliang
作者单位	1.Chongqing University,School of Computer Science,Chongqing,400044,China 2.Chongqing University,State Key Laboratory of Mechanical Transmissions,Chongqing,400044,China 3.Zhuhai and Guangdong Key Lab. of AI Multi-Modal Data Proc. BNU-HKBU U. International College Zhuhai,BNU-UIC Institute of Artificial Intelligence and Future Networks,Beijing Normal University,Guangdong,519087,China
推荐引用方式 GB/T 7714	Zheng，Zihao,Zhou，Mingliang,Shang，Zhaoweiet al. GAANet: Graph Aggregation Alignment Feature Fusion for Multispectral Object Detection[J]. IEEE Transactions on Industrial Informatics, 2025.
APA	Zheng，Zihao., Zhou，Mingliang., Shang，Zhaowei., Wei，Xuekai., Pu，Huayan., .. & Jia，Weijia. (2025). GAANet: Graph Aggregation Alignment Feature Fusion for Multispectral Object Detection. IEEE Transactions on Industrial Informatics.
MLA	Zheng，Zihao,et al."GAANet: Graph Aggregation Alignment Feature Fusion for Multispectral Object Detection". IEEE Transactions on Industrial Informatics (2025).