{"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/lifting-layers-analysis-and-applications","title":"Lifting Layers: Analysis and Applications","arxiv_id":"1803.08660","date":"2018-03-23","proceeding":"ECCV 2018 9","authors":["Peter Ochs","Tim Meinhardt","Laura Leal-Taixe","Michael Moeller"],"abstract":"The great advances of learning-based approaches in image processing and\ncomputer vision are largely based on deeply nested networks that compose linear\ntransfer functions with suitable non-linearities. Interestingly, the most\nfrequently used non-linearities in imaging applications (variants of the\nrectified linear unit) are uncommon in low dimensional approximation problems.\nIn this paper we propose a novel non-linear transfer function, called lifting,\nwhich is motivated from a related technique in convex optimization. A lifting\nlayer increases the dimensionality of the input, naturally yields a linear\nspline when combined with a fully connected layer, and therefore closes the gap\nbetween low and high dimensional approximation problems. Moreover, applying the\nlifting operation to the loss layer of the network allows us to handle\nnon-convex and flat (zero-gradient) cost functions. We analyze the proposed\nlifting theoretically, exemplify interesting properties in synthetic\nexperiments and demonstrate its effectiveness in deep learning approaches to\nimage classification and denoising.","url_abs":"http://arxiv.org/abs/1803.08660v1","url_pdf":"http://arxiv.org/pdf/1803.08660v1.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":"lifting-layers-analysis-and-applications","repo_url":"https://github.com/michimoeller/liftingLayers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}