浙江电力2024，Vol.43Issue(1)：126-132,7.DOI:10.19585/j.zjdl.202401015
面向电力缺陷场景的小样本图像生成方法
A few-shot image generation method for power defect scenarios
摘要
Abstract
Due to the limited availability of power defect data,most current defect detection methods are unable to accurately detect power system anomalies.To overcome this challenge,a few-shot image generation method is em-ployed.Building upon the improved local-fusion generative adversarial network(LoFGAN),a context-aware few-shot image generator is designed to enhance the defect detection network's capability to extract detailed features.A regularization loss based on LC-divergence is introduced to optimize the training effectiveness of the image genera-tion model on limited datasets.Experimental results reveal that the few-shot image generation method can generate effective and diverse defect data for power scenarios.The proposed model can address the issue of data unavailabil-ity in power defect scenarios.关键词
小样本图像生成/电力缺陷/上下文信息/LC-散度Key words
few-shot image generation/power defect/context-aware/LC-divergence引用本文复制引用
何宇浩,宋云海,何森,周震震,孙萌,陈毅,闫云凤..面向电力缺陷场景的小样本图像生成方法[J].浙江电力,2024,43(1):126-132,7.基金项目
浙江省科技计划项目(2022C01056) （2022C01056）
浙江省科技计划项目(LQ21F030017) （LQ21F030017）
CCF-联想蓝海科研基金 （）
