HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images
Small object detection (SOD) in remote sensing images (RSIs) is a challenging task due to scale variation, severe occlusion, and complex backgrounds, often leading to high miss and false detection rates. To address these issues, this paper proposes a novel detection framework named HSF-YOLO, which i...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4369 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849251862360883200 |
|---|---|
| author | Fujun Wang Xing Wang |
| author_facet | Fujun Wang Xing Wang |
| author_sort | Fujun Wang |
| collection | DOAJ |
| description | Small object detection (SOD) in remote sensing images (RSIs) is a challenging task due to scale variation, severe occlusion, and complex backgrounds, often leading to high miss and false detection rates. To address these issues, this paper proposes a novel detection framework named HSF-YOLO, which is designed to jointly enhance feature encoding, attention interaction, and localization precision within the YOLOv8 backbone. Specifically, we introduce three tailored modules: Hybrid Atrous Enhanced Convolution (HAEC), a Spatial–Interactive–Shuffle attention module (C2f_SIS), and a Focal Gradient Refinement Loss (FGR-Loss). The HAEC module captures multi-scale semantic and fine-grained local information through parallel atrous and standard convolutions, thereby enhancing small object representation across scales. The C2f_SIS module fuses spatial and improved channel attention with a channel shuffle strategy to enhance feature interaction and suppress background noise. The FGR-Loss incorporates gradient-aware localization, focal weighting, and separation-aware constraints to improve regression accuracy and training robustness. Extensive experiments were conducted on three public remote sensing datasets. Compared with the baseline YOLOv8, HSF-YOLO improved mAP@0.5 and mAP@0.5:0.95 by 5.7% and 4.0% on the VisDrone2019 dataset, by 2.3% and 2.5% on the DIOR dataset, and by 2.3% and 2.1% on the NWPU VHR-10 dataset, respectively. These results confirm that HSF-YOLO is a unified and effective solution for small object detection in complex RSI scenarios, offering a good balance between accuracy and efficiency. |
| format | Article |
| id | doaj-art-4fe5a05f4d0a458ab2efecf7ddae1acb |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-4fe5a05f4d0a458ab2efecf7ddae1acb2025-08-20T03:56:49ZengMDPI AGSensors1424-82202025-07-012514436910.3390/s25144369HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing ImagesFujun Wang0Xing Wang1School of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaSchool of Information Science and Engineering, Linyi University, Linyi 276000, ChinaSmall object detection (SOD) in remote sensing images (RSIs) is a challenging task due to scale variation, severe occlusion, and complex backgrounds, often leading to high miss and false detection rates. To address these issues, this paper proposes a novel detection framework named HSF-YOLO, which is designed to jointly enhance feature encoding, attention interaction, and localization precision within the YOLOv8 backbone. Specifically, we introduce three tailored modules: Hybrid Atrous Enhanced Convolution (HAEC), a Spatial–Interactive–Shuffle attention module (C2f_SIS), and a Focal Gradient Refinement Loss (FGR-Loss). The HAEC module captures multi-scale semantic and fine-grained local information through parallel atrous and standard convolutions, thereby enhancing small object representation across scales. The C2f_SIS module fuses spatial and improved channel attention with a channel shuffle strategy to enhance feature interaction and suppress background noise. The FGR-Loss incorporates gradient-aware localization, focal weighting, and separation-aware constraints to improve regression accuracy and training robustness. Extensive experiments were conducted on three public remote sensing datasets. Compared with the baseline YOLOv8, HSF-YOLO improved mAP@0.5 and mAP@0.5:0.95 by 5.7% and 4.0% on the VisDrone2019 dataset, by 2.3% and 2.5% on the DIOR dataset, and by 2.3% and 2.1% on the NWPU VHR-10 dataset, respectively. These results confirm that HSF-YOLO is a unified and effective solution for small object detection in complex RSI scenarios, offering a good balance between accuracy and efficiency.https://www.mdpi.com/1424-8220/25/14/4369remote sensing imagessmall object detectionmulti-scale feature representationattention mechanism |
| spellingShingle | Fujun Wang Xing Wang HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images Sensors remote sensing images small object detection multi-scale feature representation attention mechanism |
| title | HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images |
| title_full | HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images |
| title_fullStr | HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images |
| title_full_unstemmed | HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images |
| title_short | HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images |
| title_sort | hsf yolo a multi scale and gradient aware network for small object detection in remote sensing images |
| topic | remote sensing images small object detection multi-scale feature representation attention mechanism |
| url | https://www.mdpi.com/1424-8220/25/14/4369 |
| work_keys_str_mv | AT fujunwang hsfyoloamultiscaleandgradientawarenetworkforsmallobjectdetectioninremotesensingimages AT xingwang hsfyoloamultiscaleandgradientawarenetworkforsmallobjectdetectioninremotesensingimages |