Towards Robust Infrared Small Target Detection: A Feature-Enhanced and Sensitivity-Tunable Framework

Recently, single-frame infrared small target (SIRST) detection technology has attracted wide-spread attention. However, due to the intrinsic feature scarcity in infrared small targets, precise segmentation of small targets from complex backgrounds remains a significant challenge. Different from most existing deep learning-based methods that focus on improving network architectures, we propose a feature-enhanced and sensitivity-tunable (FEST) framework, which is compatible with existing SIRST detection networks and further enhances their detection performance. The FEST framework improves the model's robustness from two aspects: feature enhancement and target confidence regulation. For feature enhancement, on the one hand, we adopt a multi-scale fusion strategy, which can effectively improve the model's perception and adaptability to multi-scale features of multi-size targets. On the other hand, we construct an edge enhancement difficulty mining (EEDM) loss based on the analysis of the task characteristics, which helps guide the network to continuously focus on challenging target regions and edge features during training. For target confidence regulation, we design an adjustable sensitivity (AS) strategy for network post-processing. This strategy not only enhances the adaptability of the network in complex scenarios, but also significantly improves the detection rate of infrared small targets while maintaining segmentation accuracy. Extensive experimental results show that our FEST framework can significantly enhance the performance of existing SIRST detection networks. Notably, the multi-scale direction-aware network (MSDA-Net) equipped with the FEST framework won the first prize in the PRCV 2024 wide-area infrared small target detection competition.

@article{zhao2025_2407.20090,
  title={ Towards Robust Infrared Small Target Detection: A Feature-Enhanced and Sensitivity-Tunable Framework },
  author={ Jinmiao Zhao and Zelin Shi and Chuang Yu and Yunpeng Liu and Yimian Dai },
  journal={arXiv preprint arXiv:2407.20090},
  year={ 2025 }
}