{"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/on-demand-learning-for-deep-image-restoration","title":"On-Demand Learning for Deep Image Restoration","arxiv_id":"1612.01380","date":"2016-12-05","proceeding":"ICCV 2017 10","authors":["Ruohan Gao","Kristen Grauman"],"abstract":"While machine learning approaches to image restoration offer great promise,\ncurrent methods risk training models fixated on performing well only for image\ncorruption of a particular level of difficulty---such as a certain level of\nnoise or blur. First, we examine the weakness of conventional \"fixated\" models\nand demonstrate that training general models to handle arbitrary levels of\ncorruption is indeed non-trivial. Then, we propose an on-demand learning\nalgorithm for training image restoration models with deep convolutional neural\nnetworks. The main idea is to exploit a feedback mechanism to self-generate\ntraining instances where they are needed most, thereby learning models that can\ngeneralize across difficulty levels. On four restoration tasks---image\ninpainting, pixel interpolation, image deblurring, and image denoising---and\nthree diverse datasets, our approach consistently outperforms both the status\nquo training procedure and curriculum learning alternatives.","url_abs":"http://arxiv.org/abs/1612.01380v3","url_pdf":"http://arxiv.org/pdf/1612.01380v3.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":"on-demand-learning-for-deep-image-restoration","repo_url":"https://github.com/rhgao/on-demand-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1612.01380","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}