{"title":"条件gan的多类铰链损失","authors":"Ilya Kavalerov, W. Czaja","doi":"10.1109/WACV48630.2021.00133","DOIUrl":null,"url":null,"abstract":"We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset.","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"4 3","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":"{\"title\":\"A Multi-Class Hinge Loss for Conditional GANs\",\"authors\":\"Ilya Kavalerov, W. Czaja\",\"doi\":\"10.1109/WACV48630.2021.00133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset.\",\"PeriodicalId\":236300,\"journal\":{\"name\":\"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)\",\"volume\":\"4 3\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"18\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WACV48630.2021.00133\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACV48630.2021.00133","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset.