{"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/fine-tuning-handwriting-recognition-systems","title":"Fine-tuning Handwriting Recognition systems with Temporal Dropout","arxiv_id":"2102.00511","date":"2021-01-31","proceeding":null,"authors":["Edgard Chammas","Chafic Mokbel"],"abstract":"This paper introduces a novel method to fine-tune handwriting recognition systems based on Recurrent Neural Networks (RNN). Long Short-Term Memory (LSTM) networks are good at modeling long sequences but they tend to overfit over time. To improve the system's ability to model sequences, we propose to drop information at random positions in the sequence. We call our approach Temporal Dropout (TD). We apply TD at the image level as well to internal network representation. We show that TD improves the results on two different datasets. Our method outperforms previous state-of-the-art on Rodrigo dataset.","url_abs":"https://arxiv.org/abs/2102.00511v1","url_pdf":"https://arxiv.org/pdf/2102.00511v1.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":"fine-tuning-handwriting-recognition-systems","repo_url":"https://github.com/0x454447415244/HandwritingRecognitionSystem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"handwriting-recognition","task_name":"Handwriting Recognition"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"temporal-dropout","method_name":"Temporal Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}