{"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/abinet-autonomous-bidirectional-and-iterative","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","arxiv_id":"2211.10578","date":"2022-11-19","proceeding":null,"authors":["Shancheng Fang","Zhendong Mao","Hongtao Xie","Yuxin Wang","Chenggang Yan","Yongdong Zhang"],"abstract":"Scene text spotting is of great importance to the computer vision community due to its wide variety of applications. Recent methods attempt to introduce linguistic knowledge for challenging recognition rather than pure visual classification. However, how to effectively model the linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting. Firstly, the autonomous suggests enforcing explicitly language modeling by decoupling the recognizer into vision model and language model and blocking gradient flow between both models. Secondly, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for the language model which can effectively alleviate the impact of noise input. Finally, to polish ABINet++ in long text recognition, we propose to aggregate horizontal features by embedding Transformer units inside a U-Net, and design a position and content attention module which integrates character order and content to attend to character features precisely. ABINet++ achieves state-of-the-art performance on both scene text recognition and scene text spotting benchmarks, which consistently demonstrates the superiority of our method in various environments especially on low-quality images. Besides, extensive experiments including in English and Chinese also prove that, a text spotter that incorporates our language modeling method can significantly improve its performance both in accuracy and speed compared with commonly used attention-based recognizers.","url_abs":"https://arxiv.org/abs/2211.10578v2","url_pdf":"https://arxiv.org/pdf/2211.10578v2.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":"abinet-autonomous-bidirectional-and-iterative","repo_url":"https://github.com/fangshancheng/abinet-pp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"blocking","task_name":"Blocking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"text-spotting","task_name":"Text Spotting"}],"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":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"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":"max-pooling","method_name":"Max Pooling"},{"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":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-spotting-on-scut-ctw1500","task":"Text Spotting","dataset":"SCUT-CTW1500","model":"ABINet++","rank_in_archive_order":4,"of":11,"metrics":{"F-Measure (%) - Full Lexicon":"80.3","F-measure (%) - No Lexicon":"60.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.10578","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}