.png){kind=icon}
.png){kind=icon}
Return
GMTNet: Global Feature Integration Mamba–Transformer Hybrid Network for Infrared Small-Target Detection
.png){kind=icon}
PRE
AI
Z
X
Y
W
G
M
DOI：10.1109/LGRS.2026.3673619.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Infrared small-target detection (IRSTD) is crucial for surveillance, rescue, and early warning applications, but it still faces many challenges due to weak signals, limited texture, and cluttered backgrounds. Existing methods based on convolutional neural networks (CNNs) lack global context information, while methods based on Transformers and state-space models may be too complex or too smooth, resulting in missed detections. We propose a Mamba–Transformer hybrid network called GMTNet, which can selectively fuse global semantics and local details. GMTNet contains three key components: 1) a directional state-space Transformer (DiST) module for combining direction-aware long-range modeling with fine local cues; 2) a wavelet-based multidimensional lossless downsampling (WMLD) module to preserve high-frequency information during resolution reduction; and 3) a DualAug module for combining geometric and photometric perturbations for robustness. Experiments on IRSTD-1K, NUAA-SIRST, and NUDT-SIRST show that GMTNet consistently outperforms the state-of-the-art methods and can provide robust and efficient IRSTD.
Keywords:
Global–local feature integration
infrared small-target detection (IRSTD)
Mamba
state-space model (SSM)
Transformer
Journal
I
IF:
4.4
Papers:
486
Citations:
0
Organization
Cited Papers