Similar Category Enhancement Network for Discrimination on Small Object Detection
IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-18
DOI: 10.1109/tgrs.2025.3628045 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Ziji Wei und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Object detection is a fundamental procedure in the interpretation of remote sensing images. In large-scale remote sensing images, it is common to observe that the interesting objects only occupy a small area. Such objects provide limited information gain and exhibit unclear edges, often named as small objects. The inherent characteristics of small objects significantly hinder the precise localization and accurate classification of deep object detection networks. In this article, we introduce a significant challenge: the presence of similar objects among these small objects, which leads to dramatic misclassification and overall accuracy decrease. To assess this phenomenon, we propose a novel metric, similar category angle (SCA), for classification discrimination, which serves to intuitively describe the network’s effectiveness in discriminating similar category objects in its final predictions. We also propose a one-stage object detection network named similar category enhancement network (SCENet), designed to tackle the challenges associated with discriminating similar objects in small object detection (SOD) tasks. Specifically, we design SCA Loss guided by the SCA metric, which integrates SCA into the network training process, thereby enhancing the network’s capability to discriminate between similar category objects. Meanwhile, we propose Laplacian–Sobel enhancement FPN (LSE-FPN), LSE-FPN, a module that incorporates dynamic edge extraction operators into the FPN to enhance the network’s ability to detect small objects by sharpening the explicit edges of objects in the feature map. Extensive experiments conducted on SODA-A, VisDrone2019, and FAIR1M-AIR datasets demonstrate the superiority of SCENet in the SOD task, with significant improvements in detection results for both the mAP50 and SCA metrics. The code is available at https://github.com/weiziji01/SCENet
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wei, Z., Zhang, T., Sun, X., Zhuang, L., Wang, D., Marinoni, A., & Gao, L. (2025). Similar Category Enhancement Network for Discrimination on Small Object Detection. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-18. https://doi.org/10.1109/tgrs.2025.3628045
Vancouver
Wei Z, Zhang T, Sun X, Zhuang L, Wang D, Marinoni A, et al. Similar Category Enhancement Network for Discrimination on Small Object Detection. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-18. doi:10.1109/tgrs.2025.3628045
BibTeX
@article{Wei2025,
author = {Wei, Ziji and Zhang, Tianwei and Sun, Xu and Zhuang, Lina and Wang, Degang and Marinoni, Andrea and Gao, Lianru},
title = {Similar Category Enhancement Network for Discrimination on Small Object Detection},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2025},
volume = {63},
pages = {1--18},
doi = {10.1109/tgrs.2025.3628045}
}
EUVIMED