Fashion AI Literature

We concentrate on the task of Fashion AI, which entails creating images that are multimodal in terms of semantics. Previous research has attempted to use several class specific generators, which limits its application to datasets with a limited number of classes. Instead, we suggest a new Group Decreasing Network GroupDNet , which takes advantage in the generator of group convolutions and gradually reduces the percentages of the groups decoders convolutions. As a result, GroupDNet has a lot of influence over converting semantic labels to natural images and can produce plausible high quality results for datasets with a lot of groups. Experiments on a variety of difficult datasets show that GroupDNet outperforms other algorithms in the SMIS mission. We also demonstrate that GroupDNet can perform a variety of interesting synthesis tasks. Ashish Jobson | Dr. Kamalraj R "Fashion AI Literature" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42378.pdf Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/42378/fashion-ai-literature/ashish-jobson