{"title":"FIDGAN: A Generative Adversarial Network with An Inception Distance","authors":"Jina Lee, Minhyeok Lee","doi":"10.1109/ICAIIC57133.2023.10066964","DOIUrl":null,"url":null,"abstract":"Two evaluation metrics for GAN models have been proposed in existing studies: Inception score (IS) and Fréchet Inception distance (FID). We propose a new GAN model based on the idea that backpropagating the FID score would guide the GAN to efficiently learn the distribution of real images and generate high-quality images. Based on such an idea, we propose a training loss for the generator to minimize a modified FID loss. Trained with the CIFAR-10 dataset, FIDGAN exhibited an FID of 11.78, which corresponds to a reduced FID compared to an existing model called BigGAN by 20.0%.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAIIC57133.2023.10066964","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Two evaluation metrics for GAN models have been proposed in existing studies: Inception score (IS) and Fréchet Inception distance (FID). We propose a new GAN model based on the idea that backpropagating the FID score would guide the GAN to efficiently learn the distribution of real images and generate high-quality images. Based on such an idea, we propose a training loss for the generator to minimize a modified FID loss. Trained with the CIFAR-10 dataset, FIDGAN exhibited an FID of 11.78, which corresponds to a reduced FID compared to an existing model called BigGAN by 20.0%.