{"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/unsupervised-transformation-learning-via","title":"Unsupervised Transformation Learning via Convex Relaxations","arxiv_id":"1711.02226","date":"2017-11-06","proceeding":"NeurIPS 2017 12","authors":["Tatsunori B. Hashimoto","John C. Duchi","Percy Liang"],"abstract":"Our goal is to extract meaningful transformations from raw images, such as\nvarying the thickness of lines in handwriting or the lighting in a portrait. We\npropose an unsupervised approach to learn such transformations by attempting to\nreconstruct an image from a linear combination of transformations of its\nnearest neighbors. On handwritten digits and celebrity portraits, we show that\neven with linear transformations, our method generates visually high-quality\nmodified images. Moreover, since our method is semiparametric and does not\nmodel the data distribution, the learned transformations extrapolate off the\ntraining data and can be applied to new types of images.","url_abs":"http://arxiv.org/abs/1711.02226v1","url_pdf":"http://arxiv.org/pdf/1711.02226v1.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":"unsupervised-transformation-learning-via","repo_url":"https://worksheets.codalab.org/worksheets/0x4412d72b55df47e5b457dacdba91f105","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.02226","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}