HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets
To address critical challenges in tiny object detection within remote sensing imagery, including resolution–semantic imbalance, inefficient feature fusion, and insufficient localization accuracy, this study proposes Hierarchical Feature Compensation You Only Look Once 11 (HFC-YOLO11), a lightweight...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/5/195 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711219160645632 |
|---|---|
| author | Jinyin Bai Wei Zhu Zongzhe Nie Xin Yang Qinglin Xu Dong Li |
| author_facet | Jinyin Bai Wei Zhu Zongzhe Nie Xin Yang Qinglin Xu Dong Li |
| author_sort | Jinyin Bai |
| collection | DOAJ |
| description | To address critical challenges in tiny object detection within remote sensing imagery, including resolution–semantic imbalance, inefficient feature fusion, and insufficient localization accuracy, this study proposes Hierarchical Feature Compensation You Only Look Once 11 (HFC-YOLO11), a lightweight detection model based on hierarchical feature compensation. Firstly, by reconstructing the feature pyramid architecture, we preserve the high-resolution P2 feature layer in shallow networks to enhance the fine-grained feature representation for tiny targets, while eliminating redundant P5 layers to reduce the computational complexity. In addition, a depth-aware differentiated module design strategy is proposed: GhostBottleneck modules are adopted in shallow layers to improve its feature reuse efficiency, while standard Bottleneck modules are maintained in deep layers to strengthen the semantic feature extraction. Furthermore, an Extended Intersection over Union loss function (EIoU) is developed, incorporating boundary alignment penalty terms and scale-adaptive weight mechanisms to optimize the sub-pixel-level localization accuracy. Experimental results on the AI-TOD and VisDrone2019 datasets demonstrate that the improved model achieves mAP50 improvements of 3.4% and 2.7%, respectively, compared to the baseline YOLO11s, while reducing its parameters by 27.4%. Ablation studies validate the balanced performance of the hierarchical feature compensation strategy in the preservation of resolution and computational efficiency. Visualization results confirm an enhanced robustness against complex background interference. HFC-YOLO11 exhibits superior accuracy and generalization capability in tiny object detection tasks, effectively meeting practical application requirements for tiny object recognition. |
| format | Article |
| id | doaj-art-6a99e7c4e8934f83a1a97b4633fb21d8 |
| institution | DOAJ |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-6a99e7c4e8934f83a1a97b4633fb21d82025-08-20T03:14:41ZengMDPI AGComputers2073-431X2025-05-0114519510.3390/computers14050195HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing TargetsJinyin Bai0Wei Zhu1Zongzhe Nie2Xin Yang3Qinglin Xu4Dong Li5School of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaSchool of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaSchool of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaSchool of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaSchool of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaSchool of Information and Communication, National University of Defense Technology, Wuhan 430034, ChinaTo address critical challenges in tiny object detection within remote sensing imagery, including resolution–semantic imbalance, inefficient feature fusion, and insufficient localization accuracy, this study proposes Hierarchical Feature Compensation You Only Look Once 11 (HFC-YOLO11), a lightweight detection model based on hierarchical feature compensation. Firstly, by reconstructing the feature pyramid architecture, we preserve the high-resolution P2 feature layer in shallow networks to enhance the fine-grained feature representation for tiny targets, while eliminating redundant P5 layers to reduce the computational complexity. In addition, a depth-aware differentiated module design strategy is proposed: GhostBottleneck modules are adopted in shallow layers to improve its feature reuse efficiency, while standard Bottleneck modules are maintained in deep layers to strengthen the semantic feature extraction. Furthermore, an Extended Intersection over Union loss function (EIoU) is developed, incorporating boundary alignment penalty terms and scale-adaptive weight mechanisms to optimize the sub-pixel-level localization accuracy. Experimental results on the AI-TOD and VisDrone2019 datasets demonstrate that the improved model achieves mAP50 improvements of 3.4% and 2.7%, respectively, compared to the baseline YOLO11s, while reducing its parameters by 27.4%. Ablation studies validate the balanced performance of the hierarchical feature compensation strategy in the preservation of resolution and computational efficiency. Visualization results confirm an enhanced robustness against complex background interference. HFC-YOLO11 exhibits superior accuracy and generalization capability in tiny object detection tasks, effectively meeting practical application requirements for tiny object recognition.https://www.mdpi.com/2073-431X/14/5/195tiny object detectionremote sensing imagehierarchical feature compensationlightweight designYOLO11 |
| spellingShingle | Jinyin Bai Wei Zhu Zongzhe Nie Xin Yang Qinglin Xu Dong Li HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets Computers tiny object detection remote sensing image hierarchical feature compensation lightweight design YOLO11 |
| title | HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets |
| title_full | HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets |
| title_fullStr | HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets |
| title_full_unstemmed | HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets |
| title_short | HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets |
| title_sort | hfc yolo11 a lightweight model for the accurate recognition of tiny remote sensing targets |
| topic | tiny object detection remote sensing image hierarchical feature compensation lightweight design YOLO11 |
| url | https://www.mdpi.com/2073-431X/14/5/195 |
| work_keys_str_mv | AT jinyinbai hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets AT weizhu hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets AT zongzhenie hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets AT xinyang hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets AT qinglinxu hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets AT dongli hfcyolo11alightweightmodelfortheaccuraterecognitionoftinyremotesensingtargets |