Affiliation:
1. School of Information Engineering, Jiangxi University of Science and Technology, Jiangxi, China
Abstract
Due to the small size and weak characteristics of small objects, the performance of existing object detection algorithms for small objects is not ideal. In this paper, we propose a small object detection network based on feature information enhancement to improve the detection effect of small objects. In our method, two key modules, information enhancement module and dense atrous convolution module, are proposed to enhance the expression and discrimination ability of feature information. The detection accuracy of this method on PASCAL VOC, MS COCO, and UCAS-AOD data sets is 81.3%, 34.8%, and 87.0%, respectively. In addition, the detection results of this paper in detecting small objects are slightly (0.2% and 0.1%) higher than the current advanced algorithms (YOLOv4 and DETR, respectively). Moreover, when these two modules are integrated into other algorithms, such as RFBNet, it can also bring considerable improvement.
Funder
National Natural Science Foundation of China
Subject
General Mathematics,General Medicine,General Neuroscience,General Computer Science
Reference45 articles.
1. Dual-stream encoder neural networks with spectral constraint for clustering functional brain connectivity data
2. Improved deep convolutional embedded clustering with Re-selectable sample training;H. Lu;Pattern Recognition,2022
3. Survey of object detection based on deep learning;H. L. Luo;Acta Electronica Sinica,2020
4. Object detection via region-based fully convolutional networks;J. Dai,2016
5. Mask R-CNN
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献