{"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/updating-the-generator-in-ppgn-h-with","title":"Updating the generator in PPGN-h with gradients flowing through the encoder","arxiv_id":"1804.00630","date":"2018-04-02","proceeding":null,"authors":["Hesam Pakdaman"],"abstract":"The Generative Adversarial Network framework has shown success in implicitly\nmodeling data distributions and is able to generate realistic samples. Its\narchitecture is comprised of a generator, which produces fake data that\nsuperficially seem to belong to the real data distribution, and a discriminator\nwhich is to distinguish fake from genuine samples. The Noiseless Joint Plug &\nPlay model offers an extension to the framework by simultaneously training\nautoencoders. This model uses a pre-trained encoder as a feature extractor,\nfeeding the generator with global information. Using the Plug & Play network as\nbaseline, we design a new model by adding discriminators to the Plug & Play\narchitecture. These additional discriminators are trained to discern real and\nfake latent codes, which are the output of the encoder using genuine and\ngenerated inputs, respectively. We proceed to investigate whether this approach\nis viable. Experiments conducted for the MNIST manifold show that this indeed\nis the case.","url_abs":"http://arxiv.org/abs/1804.00630v1","url_pdf":"http://arxiv.org/pdf/1804.00630v1.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":"updating-the-generator-in-ppgn-h-with","repo_url":"https://github.com/hesampakdaman/ppgn-disc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"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}