Improved SinGAN for Single-Sample Airport Runway Destruction Image Generation

Abstract

Aims: To solve the problem of difficult acquisition of airport runway destruction image data. Objectives: This paper introduces SinGAN, a single-sample generative adversarial network algorithm. Methods: To address the shortcomings of SinGAN in image realism and diversity generation, an improved algorithm based on the combination of Gaussian error linear unit GELU and efficient channel attention mechanism ECANet is proposed Results: Experiments show that its generated image results are subjectively better than SinGAN and its lightweight algorithm ConSinGAN, and the model can obtain an effective balance in both quality and diversity of image generation. Conclusion: The algorithm effect is also verified using three objective evaluation metrics, and the results show that the method in this paper effectively improves the generation effect compared with SinGAN, in which the SIFID metric is reduced by 46.67%.