EUVIMEDEUVIMED entdecken
Crossref

Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection

Kejun Kang, Yixiu Liu, Yaoqi Sun, Shangdong Zhu, Fawei Ge, Wei Wang, Chenggang Yan, Zhigao Zheng

IEEE Transactions on Consumer Electronics · 2025-02 · 71 (1) · 785-795

DOI: 10.1109/tce.2024.3510096 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-02. Verfasst von Kejun Kang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precisely locating the edges of objects camouflaged as background is an exceedingly complicated task. Existing camouflaged object detection (COD) methods can accurately pinpoint the positions of objects, but the edges remain ambiguous. To tackle this challenge, we propose a multi-stage refinement framework to locate the precise edges of camouflaged objects coarse-to-fine, coined SAE, which integrates “shrink” and “expose” in each stage. In this paper, we transform the process by which humans capture object edges into a multi-stage shrinking process. Firstly, we obtain the edge probability distribution by subtracting a negative prediction result from a positive prediction result, thus proposing the positive-negative edge shrink module. The edge probability distribution from the previous stage is then explicitly propagated to the current stage to enhance the edge texture details. Second, we introduce edge exposure attention to expose significant edges, which also reflects the impact of the previous stage’s edge state and edge probability distribution on the current stage’s edge state. Finally, to eliminate state transition and edge deformation anomalies, we propose the abnormal localization restriction to ensure the proper execution of “shrink” and “expose”. Experimental results show that our model significantly outperforms recent SOTA methods on three COD benchmarks.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Kang, K., Liu, Y., Sun, Y., Zhu, S., Ge, F., Wang, W., Yan, C., & Zheng, Z. (2025). Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection. IEEE Transactions on Consumer Electronics, 71(1), 785-795. https://doi.org/10.1109/tce.2024.3510096

Vancouver

Kang K, Liu Y, Sun Y, Zhu S, Ge F, Wang W, et al. Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection. IEEE Transactions on Consumer Electronics. 2025;71(1):785-795. doi:10.1109/tce.2024.3510096

BibTeX
@article{Kang2025,
  author = {Kang, Kejun and Liu, Yixiu and Sun, Yaoqi and Zhu, Shangdong and Ge, Fawei and Wang, Wei and Yan, Chenggang and Zheng, Zhigao},
  title = {Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {1},
  pages = {785--795},
  doi = {10.1109/tce.2024.3510096}
}
Kostenlos starten →