{"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/svd-dip-overcoming-the-overfitting-problem-in","title":"SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstruction","arxiv_id":"2303.15748","date":"2023-03-28","proceeding":null,"authors":["Marco Nittscher","Michael Lameter","Riccardo Barbano","Johannes Leuschner","Bangti Jin","Peter Maass"],"abstract":"The deep image prior (DIP) is a well-established unsupervised deep learning method for image reconstruction; yet it is far from being flawless. The DIP overfits to noise if not early stopped, or optimized via a regularized objective. We build on the regularized fine-tuning of a pretrained DIP, by adopting a novel strategy that restricts the learning to the adaptation of singular values. The proposed SVD-DIP uses ad hoc convolutional layers whose pretrained parameters are decomposed via the singular value decomposition. Optimizing the DIP then solely consists in the fine-tuning of the singular values, while keeping the left and right singular vectors fixed. We thoroughly validate the proposed method on real-measured $\\mu$CT data of a lotus root as well as two medical datasets (LoDoPaB and Mayo). We report significantly improved stability of the DIP optimization, by overcoming the overfitting to noise.","url_abs":"https://arxiv.org/abs/2303.15748v3","url_pdf":"https://arxiv.org/pdf/2303.15748v3.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":"svd-dip-overcoming-the-overfitting-problem-in","repo_url":"https://github.com/educating-dip/svd_dip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"ct-reconstruction","task_name":"CT Reconstruction"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"}],"methods":[{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.15748","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}