MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection

Dense objects detection in remote sensing is challenging due to similar neighboring features, causing redundant boxes and positioning errors. To address this, we propose MSFE-Net, a multi-scale feature enhancement network designed to effectively suppress background interference and detect adjacent s...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Yuan, Xing Li, Yaoyao Ren, Lianpeng Zhang, Wei Liu, Erzhu Li
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2025.2514324
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156758105849856
author Kai Yuan
Xing Li
Yaoyao Ren
Lianpeng Zhang
Wei Liu
Erzhu Li
author_facet Kai Yuan
Xing Li
Yaoyao Ren
Lianpeng Zhang
Wei Liu
Erzhu Li
author_sort Kai Yuan
collection DOAJ
description Dense objects detection in remote sensing is challenging due to similar neighboring features, causing redundant boxes and positioning errors. To address this, we propose MSFE-Net, a multi-scale feature enhancement network designed to effectively suppress background interference and detect adjacent similar targets. Our Cascading Feature Fusion Module (CFFM) and Weighted Dilated Convolutional Pyramid (WDCP) enhance shallow texture and deep semantic features, respectively. To further reduce redundant target boxes, the Weighted Feature Fusion Enhancement Module (WFFEM) learns differential and fused features across multiple branches, thereby enriching target contextual features and suppressing background noise. Ultimately, the Multi-scale Feature Stairstep-upsampling Fusion Module (MFSFM) refines high-resolution texture and semantic features for targets across scales, using a stairstep-upsampling fusion strategy with outputs from the CFFM, WDCP, and WFFEM. Experimental results on the NWPU VHR-10 dataset show that MSFE-Net achieves 92.8% in mAP50 and 62.6% in mAP75, outperforming state-of-the-art methods such as YOLOv6 and YOLOv7. Compared to other models, MSFE-Net balances between parameter counts and computational demand, with Params slightly higher than YOLOv5s and YOLOv7-tiny and GFLOPs in a moderately high range. These results underscore MSFE-Net’s efficacy in balancing accuracy with computational demands, rendering it a highly practical option for dense object detection in remote sensing.
format Article
id doaj-art-8d07fc2c24fa45a980398bd344db3da3
institution OA Journals
issn 0883-9514
1087-6545
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Applied Artificial Intelligence
spelling doaj-art-8d07fc2c24fa45a980398bd344db3da32025-08-20T02:24:25ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452025-12-0139110.1080/08839514.2025.2514324MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object DetectionKai Yuan0Xing Li1Yaoyao Ren2Lianpeng Zhang3Wei Liu4Erzhu Li5School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaSchool of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, ChinaDense objects detection in remote sensing is challenging due to similar neighboring features, causing redundant boxes and positioning errors. To address this, we propose MSFE-Net, a multi-scale feature enhancement network designed to effectively suppress background interference and detect adjacent similar targets. Our Cascading Feature Fusion Module (CFFM) and Weighted Dilated Convolutional Pyramid (WDCP) enhance shallow texture and deep semantic features, respectively. To further reduce redundant target boxes, the Weighted Feature Fusion Enhancement Module (WFFEM) learns differential and fused features across multiple branches, thereby enriching target contextual features and suppressing background noise. Ultimately, the Multi-scale Feature Stairstep-upsampling Fusion Module (MFSFM) refines high-resolution texture and semantic features for targets across scales, using a stairstep-upsampling fusion strategy with outputs from the CFFM, WDCP, and WFFEM. Experimental results on the NWPU VHR-10 dataset show that MSFE-Net achieves 92.8% in mAP50 and 62.6% in mAP75, outperforming state-of-the-art methods such as YOLOv6 and YOLOv7. Compared to other models, MSFE-Net balances between parameter counts and computational demand, with Params slightly higher than YOLOv5s and YOLOv7-tiny and GFLOPs in a moderately high range. These results underscore MSFE-Net’s efficacy in balancing accuracy with computational demands, rendering it a highly practical option for dense object detection in remote sensing.https://www.tandfonline.com/doi/10.1080/08839514.2025.2514324
spellingShingle Kai Yuan
Xing Li
Yaoyao Ren
Lianpeng Zhang
Wei Liu
Erzhu Li
MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
Applied Artificial Intelligence
title MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
title_full MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
title_fullStr MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
title_full_unstemmed MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
title_short MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
title_sort msfe net multi scale feature enhancement network for remote sensing object detection
url https://www.tandfonline.com/doi/10.1080/08839514.2025.2514324
work_keys_str_mv AT kaiyuan msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection
AT xingli msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection
AT yaoyaoren msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection
AT lianpengzhang msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection
AT weiliu msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection
AT erzhuli msfenetmultiscalefeatureenhancementnetworkforremotesensingobjectdetection