EUVIMEDEUVIMED entdecken
Crossref

It Takes Two: Multi-Frequency Perception With Complementary Fusion Network for Complex Scene Segmentation

Jin Zhang, Ruiheng Zhang, Zhe Cao, Lixin Xu, Xi Chen, Min Xu

IEEE Transactions on Circuits and Systems for Video Technology · 2026-04 · 36 (4) · 5288-5300

DOI: 10.1109/tcsvt.2025.3626574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-04. Verfasst von Jin Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: Science and Technology Innovation 2030—Major Project, National Natural Science Foundation of China, Science and Technology on Electromechanical Dynamic Control Laboratory Funding.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Complex scene segmentation aims to segment objects with intricate details or those concealed within the background. Despite significant advancements, a persistent challenge remains: accurately identifying object edges in backgrounds with high inherent similarity and complex structures. To address this, we identify the prevalent spectral bias in image segmentation, where networks preferentially learn low-frequency information, as a key impediment to recognizing and learning object edges, which are rich in high-frequency details. To mitigate this bias, we propose MCNet, a segmentation framework designed to promote balanced frequency learning. MCNet comprises two primary components: multi-frequency perception (MP), which independently captures high-frequency details and low-frequency structural components of objects, and complementary fusion (CF), which intelligently fuses these distinct frequency features through learnable, adaptive mechanisms. Crucially, MCNet employs a novel frequency-aware consistency adversarial loss to explicitly guide the learning across different frequency bands. MCNet effectively integrates MP and CF, enhancing the detection of high-frequency details and low-frequency structures, thereby alleviating challenges posed by spectral bias. We evaluate the proposed method on complex scene segmentation tasks, including camouflaged object detection and dichotomous image segmentation. Through extensive comparisons with 31 existing methods across 8 benchmark datasets, we demonstrate the superiority of the proposed method.

Förderung

  • Science and Technology Innovation 2030—Major Project
  • National Natural Science Foundation of China
  • Science and Technology on Electromechanical Dynamic Control Laboratory Funding

Zitieren

APA

Zhang, J., Zhang, R., Cao, Z., Xu, L., Chen, X., & Xu, M. (2026). It Takes Two: Multi-Frequency Perception With Complementary Fusion Network for Complex Scene Segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 36(4), 5288-5300. https://doi.org/10.1109/tcsvt.2025.3626574

Vancouver

Zhang J, Zhang R, Cao Z, Xu L, Chen X, Xu M. It Takes Two: Multi-Frequency Perception With Complementary Fusion Network for Complex Scene Segmentation. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(4):5288-5300. doi:10.1109/tcsvt.2025.3626574

BibTeX
@article{Zhang2026,
  author = {Zhang, Jin and Zhang, Ruiheng and Cao, Zhe and Xu, Lixin and Chen, Xi and Xu, Min},
  title = {It Takes Two: Multi-Frequency Perception With Complementary Fusion Network for Complex Scene Segmentation},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {4},
  pages = {5288--5300},
  doi = {10.1109/tcsvt.2025.3626574}
}
Kostenlos starten →