An efficient single shot detector with weight-based feature fusion for small object detection
Abstract Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the limited information in features and the complex background. To further enhance the detection ac...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-06-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-36972-x |
_version_ | 1797795719383351296 |
---|---|
author | Ming Li Dechang Pi Shuo Qin |
author_facet | Ming Li Dechang Pi Shuo Qin |
author_sort | Ming Li |
collection | DOAJ |
description | Abstract Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the limited information in features and the complex background. To further enhance the detection accuracy of small objects, this paper proposes an efficient single-shot detector with weight-based feature fusion (WFFA-SSD). First, a weight-based feature fusion block is designed to adaptively fuse information from several multi-scale feature maps. The feature fusion block can exploit contextual information for feature maps with large resolutions. Then, a context attention block is applied to reinforce the local region in the feature maps. Moreover, a pyramids aggregation block is applied to combine the two feature pyramids to classify and locate target objects. The experimental results demonstrate that the proposed WFFA-SSD achieves higher mean Average Precision (mAP) under the premise of ensuring real-time performance. WFFA-SSD increases the mAP of the car by 4.12% on the test set of the CARPK. |
first_indexed | 2024-03-13T03:22:17Z |
format | Article |
id | doaj.art-809b67a0dc7b4cb3bf1dae02a6748d7d |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-13T03:22:17Z |
publishDate | 2023-06-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-809b67a0dc7b4cb3bf1dae02a6748d7d2023-06-25T11:14:54ZengNature PortfolioScientific Reports2045-23222023-06-0113111110.1038/s41598-023-36972-xAn efficient single shot detector with weight-based feature fusion for small object detectionMing Li0Dechang Pi1Shuo Qin2School of Computer Science and Technology, Nanjing University of Aeronautics and AstronauticsSchool of Computer Science and Technology, Nanjing University of Aeronautics and AstronauticsSchool of Computer Science and Technology, Nanjing University of Aeronautics and AstronauticsAbstract Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the limited information in features and the complex background. To further enhance the detection accuracy of small objects, this paper proposes an efficient single-shot detector with weight-based feature fusion (WFFA-SSD). First, a weight-based feature fusion block is designed to adaptively fuse information from several multi-scale feature maps. The feature fusion block can exploit contextual information for feature maps with large resolutions. Then, a context attention block is applied to reinforce the local region in the feature maps. Moreover, a pyramids aggregation block is applied to combine the two feature pyramids to classify and locate target objects. The experimental results demonstrate that the proposed WFFA-SSD achieves higher mean Average Precision (mAP) under the premise of ensuring real-time performance. WFFA-SSD increases the mAP of the car by 4.12% on the test set of the CARPK.https://doi.org/10.1038/s41598-023-36972-x |
spellingShingle | Ming Li Dechang Pi Shuo Qin An efficient single shot detector with weight-based feature fusion for small object detection Scientific Reports |
title | An efficient single shot detector with weight-based feature fusion for small object detection |
title_full | An efficient single shot detector with weight-based feature fusion for small object detection |
title_fullStr | An efficient single shot detector with weight-based feature fusion for small object detection |
title_full_unstemmed | An efficient single shot detector with weight-based feature fusion for small object detection |
title_short | An efficient single shot detector with weight-based feature fusion for small object detection |
title_sort | efficient single shot detector with weight based feature fusion for small object detection |
url | https://doi.org/10.1038/s41598-023-36972-x |
work_keys_str_mv | AT mingli anefficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection AT dechangpi anefficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection AT shuoqin anefficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection AT mingli efficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection AT dechangpi efficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection AT shuoqin efficientsingleshotdetectorwithweightbasedfeaturefusionforsmallobjectdetection |