EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Relevance Pooling Guidance and Class-Balanced Feature Enhancement for Fine-Grained Oriented Object Detection in Remote Sensing Images

Yu Wang, Hao Chen, Ye Zhang, Guozheng Li

Remote Sensing · 20.09.2024 · 16 (18) · 3494

DOI: 10.3390/rs16183494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 20.09.2024. Verfasst von Yu Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fine-grained object detection in remote sensing images is highly challenging due to class imbalance and high inter-class indistinguishability. The strategies employed by most existing methods to resolve these two challenges are relatively rudimentary, resulting in suboptimal model performance. To address these issues, we propose a fine-grained object-oriented detection method based on relevance pooling guidance and class balance feature enhancement. Firstly, we propose a global attention mechanism that dynamically retains spatial features pertinent to objects through relevance pooling during down-sampling, thereby enabling the model to acquire more discriminative features. Next, a class balance correction module is proposed to alleviate the class imbalance problem. This module employs feature translation and a learnable reinforcement coefficient to highlight the boundaries of tail class features while maintaining their distinctiveness. Furthermore, we present an enhanced contrastive learning strategy. By dynamically adjusting the contribution of inter-class samples and intra-class similarity measures, this strategy not only constrains inter-class feature distances but also facilitates tighter intra-class clustering, making it more suitable for imbalanced datasets. Evaluation on the FAIR1M and MAR20 datasets demonstrates that our method is superior compared to other methods in object detection and achieves 46.44 and 85.05% mean average precision, respectively.

Zitieren

APA

Wang, Y., Chen, H., Zhang, Y., & Li, G. (2024). Relevance Pooling Guidance and Class-Balanced Feature Enhancement for Fine-Grained Oriented Object Detection in Remote Sensing Images. Remote Sensing, 16(18), 3494. https://doi.org/10.3390/rs16183494

Vancouver

Wang Y, Chen H, Zhang Y, Li G. Relevance Pooling Guidance and Class-Balanced Feature Enhancement for Fine-Grained Oriented Object Detection in Remote Sensing Images. Remote Sensing. 2024;16(18):3494. doi:10.3390/rs16183494

BibTeX
@article{Wang2024,
  author = {Wang, Yu and Chen, Hao and Zhang, Ye and Li, Guozheng},
  title = {Relevance Pooling Guidance and Class-Balanced Feature Enhancement for Fine-Grained Oriented Object Detection in Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {18},
  pages = {3494},
  doi = {10.3390/rs16183494}
}
Kostenlos starten →