EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MCC-Net: Efficient Dual-Attention Network for Infrared Small-Target Detection

Xiaotian Zhou, Xin Wang, Yan Tian, Kai Jiang, Min Guo, Xuezheng Lian, Lu Ding, Quanyu Zhang, Yaqi Xue

Remote Sensing · 05.06.2026 · 18 (11) · 1858

DOI: 10.3390/rs18111858 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 05.06.2026. Verfasst von Xiaotian Zhou und 8 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent years have witnessed the emergence of numerous U-shaped deep learning segmentation methods for infrared small-target detection (IRSTD). However, increasingly complex models still suffer from false and missed detections in challenging scenarios with cluttered backgrounds and weak targets while incurring escalating computational costs. To address these limitations, this paper proposes MCC-Net, a novel and efficient IRSTD framework that achieves superior detection performance with significantly reduced computational complexity. First, we integrate Magnitude-Aware Linear Attention (MALA) and Conditionally Parameterized Convolutions (CondConv) to replace conventional attention mechanisms in skip connections and standard convolutions, respectively, endowing the model with spatial contextual modeling and enhanced feature extraction capabilities at minimal computational overhead. Second, we design an innovative Conditional Cross-Channel Fusion (CondCCF) module that establishes a complementary spatial-channel dual-attention mechanism with MALA, enabling efficient multi-scale feature fusion. Extensive comparative and ablation experiments conducted on three public benchmarks—SIRST-v1, NUDT-SIRST, and IRSTD-1K—demonstrate that MCC-Net achieves state-of-the-art mIoU scores of 77.98%, 95.43%, and 70.46%, respectively, surpassing state-of-the-art methods by 1.07%, 1.95%, and 0.95%. MCC-Net also outperforms existing approaches across multiple evaluation metrics while maintaining substantially lower computational complexity.

Förderung

  • Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences

Zitieren

APA

Zhou, X., Wang, X., Tian, Y., Jiang, K., Guo, M., Lian, X., Ding, L., Zhang, Q., & Xue, Y. (2026). MCC-Net: Efficient Dual-Attention Network for Infrared Small-Target Detection. Remote Sensing, 18(11), 1858. https://doi.org/10.3390/rs18111858

Vancouver

Zhou X, Wang X, Tian Y, Jiang K, Guo M, Lian X, et al. MCC-Net: Efficient Dual-Attention Network for Infrared Small-Target Detection. Remote Sensing. 2026;18(11):1858. doi:10.3390/rs18111858

BibTeX
@article{Zhou2026,
  author = {Zhou, Xiaotian and Wang, Xin and Tian, Yan and Jiang, Kai and Guo, Min and Lian, Xuezheng and Ding, Lu and Zhang, Quanyu and Xue, Yaqi},
  title = {MCC-Net: Efficient Dual-Attention Network for Infrared Small-Target Detection},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1858},
  doi = {10.3390/rs18111858}
}
Kostenlos starten →