{"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/rendergan-generating-realistic-labeled-data","title":"RenderGAN: Generating Realistic Labeled Data","arxiv_id":"1611.01331","date":"2016-11-04","proceeding":null,"authors":["Leon Sixt","Benjamin Wild","Tim Landgraf"],"abstract":"Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable\nperformance on many computer vision tasks. Due to their large parameter space,\nthey require many labeled samples when trained in a supervised setting. The\ncosts of annotating data manually can render the use of DCNNs infeasible. We\npresent a novel framework called RenderGAN that can generate large amounts of\nrealistic, labeled images by combining a 3D model and the Generative\nAdversarial Network framework. In our approach, image augmentations (e.g.\nlighting, background, and detail) are learned from unlabeled data such that the\ngenerated images are strikingly realistic while preserving the labels known\nfrom the 3D model. We apply the RenderGAN framework to generate images of\nbarcode-like markers that are attached to honeybees. Training a DCNN on data\ngenerated by the RenderGAN yields considerably better performance than training\nit on various baselines.","url_abs":"http://arxiv.org/abs/1611.01331v5","url_pdf":"http://arxiv.org/pdf/1611.01331v5.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":"rendergan-generating-realistic-labeled-data","repo_url":"https://github.com/berleon/deepdecoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"dcnn","method_name":"DCNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.01331","atlas_url":"https://app.syntology.ai/?focus=1611.01331","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}