@article{M13F5EFA6,
title = "Graph Convolution Network Based Feature Map Fusion Method for Multi Scale Object Detection",
journal = "Journal of KIISE, JOK",
year = "2022",
issn = "2383-630X",
doi = "10.5626/JOK.2022.49.8.627",
author = "Jaegi Hwang,Seongju Kang,Kwangsue Chung",
keywords = "deep learning,object detection,GCN,attention",
abstract = "Feature Pyramid Network (FPN) is a feature map fusion technique used to solve the multi-scale problem of object detection. However, since FPN performs feature map fusion by focusing on adjacent resolutions, there is a problem in that semantic information included in non-adjacent layers is diluted. This paper, proposes a graph convolution network (GCN)-based feature map fusion technique for multi-scale object detection. The proposed GCN-based method dynamically fuses feature map information of all layers according to learnable adjacency matrix weights. The adjacency matrix weight is generated based on the multi-scale attention mechanism to adaptively reflect the scale information of the object. The feature map fusion process is performed through a matrix multiplication operation between adjacency matrix and a feature node matrix. The performance of the proposed method was verified by showing that it improves the multi-scale object detection performance in the PASCAL-VOC benchmark dataset compared to the existing FPN method."
}