{"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/easter2-0-improving-convolutional-models-for","title":"Easter2.0: Improving convolutional models for handwritten text recognition","arxiv_id":"2205.14879","date":"2022-05-30","proceeding":null,"authors":["Kartik Chaudhary","Raghav Bali"],"abstract":"Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and effective data augmentation technique 'Tiling and Corruption (TACO)' relevant for the task of HTR/OCR. Our work achieves state-of-the-art results on IAM handwriting database when trained using only publicly available training data. In our experiments, we also present the impact of TACO augmentations and Squeeze-and-Excitation (SE) on text recognition accuracy. We further show that Easter2.0 is suitable for few-shot learning tasks and outperforms current best methods including Transformers when trained on limited amount of annotated data. Code and model is available at: https://github.com/kartikgill/Easter2","url_abs":"https://arxiv.org/abs/2205.14879v1","url_pdf":"https://arxiv.org/pdf/2205.14879v1.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":"easter2-0-improving-convolutional-models-for","repo_url":"https://github.com/kartikgill/easter2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"htr","task_name":"HTR"},{"task_slug":"handwritten-text-recognition","task_name":"Handwritten Text Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/handwritten-text-recognition-on-iam","task":"Handwritten Text Recognition","dataset":"IAM","model":"Easter2.0","rank_in_archive_order":10,"of":17,"metrics":{"CER":"6.21"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14879","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}