文献类型：期刊文献

英文题名：Graphion: graph neural network-based visual correlation feature extraction module

作者：Chu, Chengqian[1];Li, Shijia[1];Yu, Xingui[1];Wan, Yongjing[1];Jiang, Cuiling[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Dept Elect & Commun Engn, Shanghai, Peoples R China

年份：2024

卷号：33

期号：1

外文期刊名：JOURNAL OF ELECTRONIC IMAGING

收录：;EI(收录号：20241115722802);WOS:【SCI-EXPANDED(收录号:WOS:001173268100044)】；

语种：英文

外文关键词：correlation feature; computer vision; graph neural network; adjacency relations; message passing and aggregation

摘要：Global contextual features are essential in computer vision tasks. Traditional convolutional networks are limited by the size of the convolutional kernel, resulting in a limited receptive field for each layer of the network. To address this issue, transformers introduced global attention, which has demonstrated excellent performance in natural language processing and has been widely applied in visual tasks. However, both convolutional networks and transformer models are constrained by the arrangement of data in Euclidean space, making it challenging to effectively extract features of irregular objects and complex scenes. We propose a graph neural network-based module (Graphion) for extracting global contextual features. Graphion maps the feature maps into a non-Euclidean space, establishes adjacency relationships among image patches, and uses a graph neural network for message passing and aggregation operations on the obtained node features, enabling the learning of correlation information from the graph structure. Consequently, it facilitates more efficient feature extraction of irregular object instances. Graphion is flexible and portable, allowing integration into visual feature extraction backbones. Extensive experiments were conducted on multiple datasets, including MS COCO, ADE20K, and ImageNet64. The proposed Graphion method demonstrates outstanding performance in object detection, segmentation, and classification.