SANet: Selective Attention Network for Infrared Small Target Detection

2026-10-07

AI Summary

This study addresses the challenge of balancing detection accuracy and false alarm rate in infrared small target detection by proposing a selective attention network. Specifically, a dual-path semantic perception module is designed, integrating standard and pinwheel-shaped convolutions with spatial-channel attention mechanisms to enhance target-background discrimination. Furthermore, an adaptive feature fusion strategy employing spatially variable weights is introduced to overcome the limitations of static skip connections, thereby optimizing multi-scale feature integration. Extensive experiments on three public benchmarks demonstrate that the proposed method achieves up to a 4.32 percentage point improvement in IoU over the second-best approach, while significantly reducing the false alarm rate and increasing the detection probability.

Abstract

Infrared small target detection aims to accurately identify and locate dim targets in complex backgrounds and supports applications such as maritime surveillance and military search and rescue. However, the small size and weak contrast of infrared targets make it difficult to balance detection accuracy and false alarms. This paper proposes a selective attention network (SANet) for infrared small target detection. A dual-path semantic-aware module combines standard and pinwheel-shaped convolutions to preserve local spatial consistency and capture broader contextual information. Spatial and channel attention further refine the features and improve target-background discrimination. To address the limitations of static skip connections in U-Net, a selective attention fusion module adaptively integrates features across scales using spatially varying weights. It selectively enhances salient regions and improves discrimination between true targets and false alarms. Experiments on three public benchmarks, NUAA-SIRST, IRSTD-1K, and NUDT-SIRST, show that SANet achieves competitive performance in intersection over union (IoU), normalized IoU, detection probability, and false alarm rate. Its IoU exceeds that of the second-best method by 1.93, 4.32, and 2.21 percentage points, respectively. These results support the effectiveness of SANet in dim-target perception, discriminative feature representation, and background suppression.

Problem

• Infrared small target detection
• dim targets
• false alarm rate
• complex backgrounds

Innovation

• Infrared small target detection
• Selective attention network
• Pinwheel-shaped convolution
• Dual-path semantic-aware module
• Adaptive feature fusion