APTNet: Adaptive Partial Transformer Network for Infrared Small Target Detection
IEEE Sensors Journal · 15.05.2025 · 25 (10) · 17960-17974
DOI: 10.1109/jsen.2025.3559093 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.05.2025. Verfasst von Yingmei Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Gan-Po Talents Support Program of Jiangxi Province—Urgently Needed Overseas Talent Program, Early-Career Young Science and Technology Talent Training Project of Jiangxi Province.
Abstract (Originalsprache)
Infrared small target detection (IRSTD) plays a vital role in various applications such as surveillance and rescue missions. However, existing methods struggle to effectively integrate contextual information for small targets, with background noise and limited long-distance dependency learning further constraining detection performance. To address these issues, this article proposes a novel adaptive partial transformer network based on asymmetric U-Net architecture, namely APTNet, which enhances contextual information integration and accurately detects small objects in complex scenes, improving detection performance. Specifically, a double residual attention block (DRAB) is designed to enhance the contrast of dim targets within complex backgrounds through channel and spatial attention mechanisms, thereby improving discrimination capability for small targets. Furthermore, leveraging the context pooling connections and DRAB output features, an adaptive partial transformer block (APTB) is proposed. This block first proposes an adaptive channel splitting factor, achieving contextual information integration and long-distance dependency learning with low computational overhead. Extensive experiments on two public datasets demonstrate that the proposed method significantly outperforms the existing state-of-the-art IRSTD methods in terms of intersection over union (IoU), probability of detection ( ${P}_{d}$ ), and false alarm rate ( ${F}_{a}$ ). The implementation of our code can be accessed at https://github.com/Wangtao-Bao/APTNet.
Förderung
- National Natural Science Foundation of China
- Gan-Po Talents Support Program of Jiangxi Province—Urgently Needed Overseas Talent Program
- Early-Career Young Science and Technology Talent Training Project of Jiangxi Province
- Natural Science Foundation of Jiangxi Province
- Graduate Innovation Special Foundation Project of Jiangxi Province
- 19th Student Research Project of Jiangxi University of Finance and Economics
Zitieren
APA
Zhang, Y., Bao, W., Wan, W., Xiao, Q., Tang, Y., Zou, X., Huang, L., Zhong, K., & Lan, Y. (2025). APTNet: Adaptive Partial Transformer Network for Infrared Small Target Detection. IEEE Sensors Journal, 25(10), 17960-17974. https://doi.org/10.1109/jsen.2025.3559093
Vancouver
Zhang Y, Bao W, Wan W, Xiao Q, Tang Y, Zou X, et al. APTNet: Adaptive Partial Transformer Network for Infrared Small Target Detection. IEEE Sensors Journal. 2025;25(10):17960-17974. doi:10.1109/jsen.2025.3559093
BibTeX
@article{Zhang2025,
author = {Zhang, Yingmei and Bao, Wangtao and Wan, Weiguo and Xiao, Qin and Tang, Yingjun and Zou, Xueting and Huang, Liu and Zhong, Kaichen and Lan, Yuhao},
title = {APTNet: Adaptive Partial Transformer Network for Infrared Small Target Detection},
journal = {IEEE Sensors Journal},
year = {2025},
volume = {25},
number = {10},
pages = {17960--17974},
doi = {10.1109/jsen.2025.3559093}
}
EUVIMED