{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/srgan-training-dataset-matters","title":"SRGAN: Training Dataset Matters","arxiv_id":"1903.09922","date":"2019-03-24","proceeding":null,"authors":["Nao Takano","Gita Alaghband"],"abstract":"Generative Adversarial Networks (GANs) in supervised settings can generate\nphoto-realistic corresponding output from low-definition input (SRGAN). Using\nthe architecture presented in the SRGAN original paper [2], we explore how\nselecting a dataset affects the outcome by using three different datasets to\nsee that SRGAN fundamentally learns objects, with their shape, color, and\ntexture, and redraws them in the output rather than merely attempting to\nsharpen edges. This is further underscored with our demonstration that once the\nnetwork learns the images of the dataset, it can generate a photo-like image\nwith even a slight hint of what it might look like for the original from a very\nblurry edged sketch. Given a set of inference images, the network trained with\nthe same dataset results in a better outcome over the one trained with\narbitrary set of images, and we report its significance numerically with\nFrechet Inception Distance score [22].","url_abs":"http://arxiv.org/abs/1903.09922v1","url_pdf":"http://arxiv.org/pdf/1903.09922v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"srgan-training-dataset-matters","repo_url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/SRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"pixelshuffle","method_name":"PixelShuffle"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"srgan","method_name":"SRGAN"},{"method_slug":"srgan-residual-block","method_name":"SRGAN Residual Block"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vgg-loss","method_name":"VGG Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}