{"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/learning-to-avoid-errors-in-gans-by","title":"Learning to Avoid Errors in GANs by Manipulating Input Spaces","arxiv_id":"1707.00768","date":"2017-07-03","proceeding":null,"authors":["Alexander B. Jung"],"abstract":"Despite recent advances, large scale visual artifacts are still a common\noccurrence in images generated by GANs. Previous work has focused on improving\nthe generator's capability to accurately imitate the data distribution\n$p_{data}$. In this paper, we instead explore methods that enable GANs to\nactively avoid errors by manipulating the input space. The core idea is to\napply small changes to each noise vector in order to shift them away from areas\nin the input space that tend to result in errors. We derive three different\narchitectures from that idea. The main one of these consists of a simple\nresidual module that leads to significantly less visual artifacts, while only\nslightly decreasing diversity. The module is trivial to add to existing GANs\nand costs almost zero computation and memory.","url_abs":"http://arxiv.org/abs/1707.00768v1","url_pdf":"http://arxiv.org/pdf/1707.00768v1.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":"learning-to-avoid-errors-in-gans-by","repo_url":"https://github.com/aleju/gan-error-avoidance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}