A Semi‐Supervised Learning Framework for Infrared Small Target Detection Using Pseudo‐Labelling and Two‐Dimensional Gaussian Prediction Modelling

Infrared small target detection faces significant challenges due to limited labelled data and complex background interference. This paper proposes a semi‐supervised learning framework that integrates pseudo‐labelling and two‐dimensional Gaussian prediction modelling to address these challenges. By leveraging unlabelled data through adaptive pseudo‐label generation, the framework enhances model generalisation. A novel two‐dimensional Gaussian prediction model is introduced during inference to characterise target spatial distributions, enabling precise localisation under noisy backgrounds. Additionally, a correlation‐aware loss function optimises the prediction model parameters by enforcing physical constraints between amplitude and spatial spread. Experiments on the SIRST dataset demonstrate state‐of‐the‐art performance, achieving 0.05 higher F1‐score and 4.9% higher AP compared to existing methods. This framework provides a robust solution for infrared small target detection in surveillance and remote sensing applications.