EUVIMEDEUVIMED entdecken
Crossref

MTMLNet: Multi-Task Mutual Learning Network for Infrared Small Target Detection and Segmentation

Bo Yang, Fengqian Li, Songliang Zhao, Wei Wang, Jun Luo, Huayan Pu, Mingliang Zhou, Yangjun Pi

IEEE Transactions on Image Processing · 2025 · 34 · 4414-4425

DOI: 10.1109/tip.2025.3587576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Bo Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared small target detection has been extensively studied due to its wide range of applications. Most studies treat infrared small target detection as an independent task, either as a detection-based or a segmentation-based, failing to fully leverage the supervisory information from different annotation forms. To address this issue, we propose a multi-task mutual learning network (MTMLNet) specifically designed for infrared small targets, aiming to enhance both detection and segmentation performance by effectively utilizing various forms of supervisory information. Specifically, we design a multi-stage feature aggregation (MFA) module capable of capturing features with varying gradients and receptive fields simultaneously. Additionally, a hybrid pooling down-sampling (HPDown) module is proposed to mitigate information loss during the down-sampling process of infrared small targets. Finally, the hierarchical feature fusion (HFF) module is designed to adaptively select and fuse features from different semantic layers, learning the optimal way to fuse features across semantic layers. The results on IRSTD-1k and SIRST-V2 datasets show that our proposed MTMLNet achieves state-of-the-art (SOTA) performance in both detection-based and segmentation-based methods. The codes are available at https://github.com/YangBo0411/MTMLNet.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Yang, B., Li, F., Zhao, S., Wang, W., Luo, J., Pu, H., Zhou, M., & Pi, Y. (2025). MTMLNet: Multi-Task Mutual Learning Network for Infrared Small Target Detection and Segmentation. IEEE Transactions on Image Processing, 34, 4414-4425. https://doi.org/10.1109/tip.2025.3587576

Vancouver

Yang B, Li F, Zhao S, Wang W, Luo J, Pu H, et al. MTMLNet: Multi-Task Mutual Learning Network for Infrared Small Target Detection and Segmentation. IEEE Transactions on Image Processing. 2025;34:4414-4425. doi:10.1109/tip.2025.3587576

BibTeX
@article{Yang2025,
  author = {Yang, Bo and Li, Fengqian and Zhao, Songliang and Wang, Wei and Luo, Jun and Pu, Huayan and Zhou, Mingliang and Pi, Yangjun},
  title = {MTMLNet: Multi-Task Mutual Learning Network for Infrared Small Target Detection and Segmentation},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {4414--4425},
  doi = {10.1109/tip.2025.3587576}
}
Kostenlos starten →