Research Article
AgBFPN: Attention Guided Bidirectional Feature Pyramid Network for Object Detection
@INPROCEEDINGS{10.1007/978-3-031-32443-7_28, author={Lanjie Jiang and Xiang Zhang and Ruijing Yang and Yudie Liu}, title={AgBFPN: Attention Guided Bidirectional Feature Pyramid Network for Object Detection}, proceedings={Mobile Networks and Management. 12th EAI International Conference, MONAMI 2022, Virtual Event, October 29-31, 2022, Proceedings}, proceedings_a={MONAMI}, year={2023}, month={5}, keywords={Deep learning Object detection Feature pyramid network Attentional mechanisms}, doi={10.1007/978-3-031-32443-7_28} }- Lanjie Jiang
Xiang Zhang
Ruijing Yang
Yudie Liu
Year: 2023
AgBFPN: Attention Guided Bidirectional Feature Pyramid Network for Object Detection
MONAMI
Springer
DOI: 10.1007/978-3-031-32443-7_28
Abstract
Object detection is increasingly in demand in IoT service applications. Deep learning based object detection algorithms are now in fashion. As the most popular multi-scale object detection network at present, Feature Pyramid Network achieves feature augmentation by fusing features of neighboring layers. It is widely used in the most advanced object detectors to detect objects of different scales. In this paper, we propose a new attention mechanism guided bidirectional feature pyramid architecture named AgBFPN to enhance the transfer of semantic and spatial information between each feature map. We design Channel Attention Guided Fusion(CAGF) Module and Spatial Attention Guided Fusion(SAGF) Module to enhance feature fusion. The CAGF mitigates the loss of information induced by channel reduction and better transfers the semantic information from high-level to low-level features. The SAGF passes the rich spatial information of shallow features into deep features. Our experiments show that AgBFPN achieves higher Average Precision for multi-scale object detection.
