Journal
MULTIMEDIA TOOLS AND APPLICATIONS
Volume 80, Issue 8, Pages 11539-11556Publisher
SPRINGER
DOI: 10.1007/s11042-020-10191-2
Keywords
Object detection; SSD; Multi-scale feature; Attention mechanism
Categories
Funding
- Scientific Research Fund of Hunan Provincial Education Department of China [17A007]
- Teaching Reform and Research Project of Hunan Province of China
Ask authors/readers for more resources
The Single Shot MultiBox Detector(SSD) uses multi-scale feature maps for object detection and has outstanding performance. However, as a one-stage detection method, SSD struggles to quickly identify significant areas of objects. Our proposed enhanced SSD method, MA-SSD, utilizes interactive multi-scale attention features to improve feature representation and detection accuracy, while ensuring detection efficiency through a parallel structure. This method achieves competitive performance on the public dataset PascalVOC.
Single Shot MultiBox Detector (SSD) method using multi-scale feature maps for object detection, showing outstanding performance in object detection task. However, as a one-stage detection method, it's difficult for SSD methods to quickly notice significant areas of objects in the image. In the SSD network structure, feature maps of different scales are used to independently predict object, and there is a lack of interaction between low-level feature maps and high-level feature maps. In this paper we propose an enhanced SSD method using interactive multi-scale attention features (MA-SSD). Our method uses the attention mechanism to generate attention features of multiple scales and adds it to the original detection branch of the SSD method, which effectively enhances the feature representation ability and improves the detection accuracy. At the same time, the feature of different detection scales interacts with each other, and all the detection branches in our method have a parallel structure, which ensures the detection efficiency. Our proposed method achieves competitive performance on the public dataset PascalVOC.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available