{"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/image-completion-on-cifar-10","title":"Image Completion on CIFAR-10","arxiv_id":"1810.03213","date":"2018-10-07","proceeding":null,"authors":["Mason Swofford"],"abstract":"This project performed image completion on CIFAR-10, a dataset of 60,000\n32x32 RGB images, using three different neural network architectures: fully\nconvolutional networks, convolutional networks with fully connected layers, and\nencoder-decoder convolutional networks. The highest performing model was a deep\nfully convolutional network, which was able to achieve a mean squared error of\n.015 when comparing the original image pixel values with the predicted pixel\nvalues. As well, this network was able to output in-painted images which\nappeared real to the human eye.","url_abs":"http://arxiv.org/abs/1810.03213v1","url_pdf":"http://arxiv.org/pdf/1810.03213v1.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":"image-completion-on-cifar-10","repo_url":"https://github.com/mswoff/Image-Completion-on-CIFAR-10","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}