Search papers, labs, and topics across Lattice.
The paper introduces SSDDPM, a single SAR image generation method based on a denoising diffusion probabilistic model to address the scarcity of high-quality SAR images for target detection tasks. SSDDPM employs a single-scale architecture to prevent noise accumulation and incorporates attention modules in the generator's sampling layer for enhanced feature extraction and redundant information suppression. Experimental results on ship target datasets demonstrate that SSDDPM outperforms SinGAN and ExSinGAN in terms of SIFID, SSIM, LPIPS, and generation diversity.
Generate realistic SAR imagery from just a single training example using a novel diffusion model architecture, outperforming existing single-image generation techniques.
The limited availability of high-quality SAR images severely affects the accuracy and robustness of target detection, classification, and segmentation. To solve this problem, a novel image generation method based on a diffusion model is introduced that requires only one training sample to generate a realistic SAR image. We propose a single-scale architecture to avoid image noise accumulation. In addition, an attention module for the sampling layer in the generator for improving feature extraction is designed. Then, an information-guided attention module is proposed to suppress redundant information. Ship targets were selected as the research objects, and the proposed method was tested using an open-source dataset. We also built our own Sentinel-1 dataset to increase the number of challenges. The experimental results show that our method is optimal compared with the classical method SinGAN. Specifically, the SIFID is decreased from 4.80โรโ10^(-4) to 1.66โรโ10^(-7), the SSIM is improved from 0.07 to 0.51, and the LPIPS is decreased from 0.61 to 0.23. Compared with that of ExSinGAN, generation diversity increases by 27.35%.
