{"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/scheduled-denoising-autoencoders","title":"Scheduled denoising autoencoders","arxiv_id":"1406.3269","date":"2014-06-12","proceeding":null,"authors":["Krzysztof J. Geras","Charles Sutton"],"abstract":"We present a representation learning method that learns features at multiple\ndifferent levels of scale. Working within the unsupervised framework of\ndenoising autoencoders, we observe that when the input is heavily corrupted\nduring training, the network tends to learn coarse-grained features, whereas\nwhen the input is only slightly corrupted, the network tends to learn\nfine-grained features. This motivates the scheduled denoising autoencoder,\nwhich starts with a high level of noise that lowers as training progresses. We\nfind that the resulting representation yields a significant boost on a later\nsupervised task compared to the original input, or to a standard denoising\nautoencoder trained at a single noise level. After supervised fine-tuning our\nbest model achieves the lowest ever reported error on the CIFAR-10 data set\namong permutation-invariant methods.","url_abs":"http://arxiv.org/abs/1406.3269v3","url_pdf":"http://arxiv.org/pdf/1406.3269v3.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":"scheduled-denoising-autoencoders","repo_url":"https://github.com/shreya2509/Scheduled-Denoising-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.3269","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}