{"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/joint-visual-denoising-and-classification","title":"Joint Visual Denoising and Classification using Deep Learning","arxiv_id":"1612.01075","date":"2016-12-04","proceeding":null,"authors":["Gang Chen","Yawei Li","Sargur N. Srihari"],"abstract":"Visual restoration and recognition are traditionally addressed in pipeline\nfashion, i.e. denoising followed by classification. Instead, observing\ncorrelations between the two tasks, for example clearer image will lead to\nbetter categorization and vice visa, we propose a joint framework for visual\nrestoration and recognition for handwritten images, inspired by advances in\ndeep autoencoder and multi-modality learning. Our model is a 3-pathway deep\narchitecture with a hidden-layer representation which is shared by multi-inputs\nand outputs, and each branch can be composed of a multi-layer deep model. Thus,\nvisual restoration and classification can be unified using shared\nrepresentation via non-linear mapping, and model parameters can be learnt via\nbackpropagation. Using MNIST and USPS data corrupted with structured noise, the\nproposed framework performs at least 20\\% better in classification than\nseparate pipelines, as well as clearer recovered images. The noise model and\nthe reproducible source code is available at\n{\\url{https://github.com/ganggit/jointmodel}}.","url_abs":"http://arxiv.org/abs/1612.01075v1","url_pdf":"http://arxiv.org/pdf/1612.01075v1.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":"joint-visual-denoising-and-classification","repo_url":"https://github.com/ganggit/jointmodel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"classification","task_name":"General 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}