EUVIMEDEUVIMED entdecken
Crossref

Spatial Residual for Underwater Object Detection

Jingchun Zhou, Zongxin He, Dehuan Zhang, Siyuan Liu, Xianping Fu, Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-06 · 47 (6) · 4996-5013

DOI: 10.1109/tpami.2025.3548652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-06. Verfasst von Jingchun Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 98-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Intelligent Policing Key Laboratory of Sichuan Province, High-Performance Computing Center of Dalian Maritime University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature drift is caused by the dynamic coupling of target features and degradation factors, which reduce underwater detector performance. We redefine feature drift as the instability of target features within boundary constraints while solving partial differential equations (PDEs). From this insight, we propose the Spatial Residual (SR) block, which uses SkipCut to establish effective constraints across the network width for solving PDEs and optimizes the solution space. It is implemented as a general-purpose backbone with 5 Spatial Residuals (BSR5) for complex feature scenarios. Specifically, BSR5 extracts discrete channel slices through SkipCut, where each sliced feature is parsed within the appropriate data capacity. In gradient backpropagation, SkipCut functions as a ShortCut, optimizing information flow and gradient allocation to enhance performance and accelerate training. Experiments on the RUOD dataset show that BSR5-integrated DETRs and YOLOs achieve state-of-the-art results for conventional and end-to-end detectors. Specifically, our BSR5-DETR improves 1.3% and 2.7% AP than RT-DETR with ResNet-101, while reducing parameters by 41.6% and 6.6%, respectively. Further validation highlights BSR5's strong convergence and robustness, especially in training from scratch scenarios, making it well suited for data-scarce, resource-constrained, and real-time tasks.

Förderung

  • National Natural Science Foundation of China
  • Intelligent Policing Key Laboratory of Sichuan Province
  • High-Performance Computing Center of Dalian Maritime University

Zitieren

APA

Zhou, J., He, Z., Zhang, D., Liu, S., Fu, X., & Li, X. (2025). Spatial Residual for Underwater Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(6), 4996-5013. https://doi.org/10.1109/tpami.2025.3548652

Vancouver

Zhou J, He Z, Zhang D, Liu S, Fu X, Li X. Spatial Residual for Underwater Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(6):4996-5013. doi:10.1109/tpami.2025.3548652

BibTeX
@article{Zhou2025,
  author = {Zhou, Jingchun and He, Zongxin and Zhang, Dehuan and Liu, Siyuan and Fu, Xianping and Li, Xuelong},
  title = {Spatial Residual for Underwater Object Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {6},
  pages = {4996--5013},
  doi = {10.1109/tpami.2025.3548652}
}
Kostenlos starten →