{"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/multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","arxiv_id":"2209.03592","date":"2022-09-08","proceeding":null,"authors":["Peng Wang","Cheng Da","Cong Yao"],"abstract":"Scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this challenging problem, numerous innovative methods have been successively proposed and incorporating linguistic knowledge into STR models has recently become a prominent trend. In this work, we first draw inspiration from the recent progress in Vision Transformer (ViT) to construct a conceptually simple yet powerful vision STR model, which is built upon ViT and outperforms previous state-of-the-art models for scene text recognition, including both pure vision models and language-augmented methods. To integrate linguistic knowledge, we further propose a Multi-Granularity Prediction strategy to inject information from the language modality into the model in an implicit way, i.e. , subword representations (BPE and WordPiece) widely-used in NLP are introduced into the output space, in addition to the conventional character level representation, while no independent language model (LM) is adopted. The resultant algorithm (termed MGP-STR) is able to push the performance envelop of STR to an even higher level. Specifically, it achieves an average recognition accuracy of 93.35% on standard benchmarks. Code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/MGP-STR.","url_abs":"https://arxiv.org/abs/2209.03592v2","url_pdf":"https://arxiv.org/pdf/2209.03592v2.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":"multi-granularity-prediction-for-scene-text","repo_url":"https://github.com/alibabaresearch/advancedliteratemachinery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-granularity-prediction-for-scene-text","repo_url":"https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/MGP-STR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multi-granularity-prediction-for-scene-text","repo_url":"https://github.com/topdu/openocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-coco-text","task":"Scene Text Recognition","dataset":"COCO-Text","model":"MGP-STR","rank_in_archive_order":2,"of":4,"metrics":{"1:1 Accuracy":"81.7"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-cute80","task":"Scene Text Recognition","dataset":"CUTE80","model":"MGP-STR","rank_in_archive_order":4,"of":18,"metrics":{"Accuracy":"99.31"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-ic19-art","task":"Scene Text Recognition","dataset":"IC19-Art","model":"MGP-STR","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy (%)":"85.5"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"MGP-STR","rank_in_archive_order":4,"of":38,"metrics":{"Accuracy":"98.5"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"MGP-STR","rank_in_archive_order":5,"of":27,"metrics":{"Accuracy":"90.9"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-iiit5k","task":"Scene Text Recognition","dataset":"IIIT5k","model":"MGP-STR","rank_in_archive_order":8,"of":17,"metrics":{"Accuracy":"98.8"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"MGP-STR","rank_in_archive_order":4,"of":37,"metrics":{"Accuracy":"98.6"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-svtp","task":"Scene Text Recognition","dataset":"SVTP","model":"MGP-STR","rank_in_archive_order":2,"of":17,"metrics":{"Accuracy":"98.3"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-uber-text","task":"Scene Text Recognition","dataset":"Uber-Text","model":"MGP-STR","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy (%)":"91.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.03592","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}