{"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/manifold-mixup-improves-text-recognition-with","title":"Manifold Mixup improves text recognition with CTC loss","arxiv_id":"1903.04246","date":"2019-03-11","proceeding":null,"authors":["Bastien Moysset","Ronaldo Messina"],"abstract":"Modern handwritten text recognition techniques employ deep recurrent neural\nnetworks. The use of these techniques is especially efficient when a large\namount of annotated data is available for parameter estimation. Data\naugmentation can be used to enhance the performance of the systems when data is\nscarce. Manifold Mixup is a modern method of data augmentation that meld two\nimages or the feature maps corresponding to these images and the targets are\nfused accordingly. We propose to apply the Manifold Mixup to text recognition\nwhile adapting it to work with a Connectionist Temporal Classification cost. We\nshow that Manifold Mixup improves text recognition results on various languages\nand datasets.","url_abs":"http://arxiv.org/abs/1903.04246v1","url_pdf":"http://arxiv.org/pdf/1903.04246v1.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":"manifold-mixup-improves-text-recognition-with","repo_url":"https://github.com/simplify23/Ultra_light_OCR_No.11","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"handwritten-text-recognition","task_name":"Handwritten Text Recognition"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[{"method_slug":"manifold-mixup","method_name":"Manifold Mixup"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}