Enhancing Infrared Small Target Detection Using Learnable Graph-Attention and Heat Equation Techniques

Due to the thermal noise caused by heat diffusion during the imaging process, the edge shape of the infrared small target detection (IRSTD) in remote sensing becomes blurred. This degrades the performance of the subsequent feature extraction. To address such a problem, we propose three modules based on deep learning. First, we design a heat equation block (HEB) by combining the heat equation in the frequency domain with a convolutional network to reproduce heat diffusion on the image. Then, a graph attention filter (GAF) is designed, which aggregates the graph node features and adjacent difference features of the graph structure. By learning the change of the features before and after the diffusion, thermal noise is reduced. Moreover, the multiscale features are fused through customized multiscale residual fusion block (MRFB). Experimental results show that the proposed method achieves an intersection over union (IoU) of 80.01% and 69.20% on the NUAA-SIRST and IRSTD-1K datasets, respectively, outperforming other advanced methods and verifying the effectiveness of the proposed method in remote sensing under various and complex backgrounds.