EUVIMEDEUVIMED entdecken
Crossref

Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images

Zebin Wu, Shangdong Zheng, Yang Xu, Le Wang, Zhihui Wei, Gang Hua

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-04 · 48 (4) · 4553-4569

DOI: 10.1109/tpami.2025.3646464 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-04. Verfasst von Zebin Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Jiangsu Provincial Innovation Support Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly-supervised object detection (WSOD) learns detectors with only image-level classification annotations. Without precise instance-level labels, most previous WSOD methods in remote sensing images (RSIs) select the highest-scoring proposals as the final detection results, which are confronted by two major challenges: (1) instances with small scale or rare poses are easily neglected; (2) optimizing network by the top-scoring region inevitably overlooks many valuable candidate proposals. To mitigate the above-mentioned challenges, we propose a data-driven bidirectional spatial-adaptive network (BSANet). It contains a forward-reverse spatial dropout (FRSD) module to reduce instance ambiguity induced from extreme scales and poses, as well as crowded scene, and to better excavate the entire instances. From attention learning perspective, the proposed FRSD is conceptually similar to a data-driven hard attention mechanism, which adaptively samples and reconstructs the spatially related regions for mining more latent feature responses. Meanwhile, our FRSD effectively alleviates the inherent problem that non-parametric hard attention learning fashion cannot adapt to different datasets. In addition, we build a soft attention branch to simultaneously model soft pixel-level and hard region-level attention information for exploring the complementary benefit between soft and hard attention learning. We evaluate our BSANet on the challenging NWPU VHR-10.v2 and DIOR datasets. Experimental results demonstrate that our method sets a new state-of-the-art.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Jiangsu Provincial Innovation Support Program
  • Jiangsu Provincial Key Research and Development Program
  • Jiangsu Provincial Natural Science Foundation of China
  • Natural Science Research Startup Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications

Zitieren

APA

Wu, Z., Zheng, S., Xu, Y., Wang, L., Wei, Z., & Hua, G. (2026). Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4553-4569. https://doi.org/10.1109/tpami.2025.3646464

Vancouver

Wu Z, Zheng S, Xu Y, Wang L, Wei Z, Hua G. Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(4):4553-4569. doi:10.1109/tpami.2025.3646464

BibTeX
@article{Wu2026,
  author = {Wu, Zebin and Zheng, Shangdong and Xu, Yang and Wang, Le and Wei, Zhihui and Hua, Gang},
  title = {Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {4},
  pages = {4553--4569},
  doi = {10.1109/tpami.2025.3646464}
}
Kostenlos starten →