{"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/vision-language-pre-training-for-boosting","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","arxiv_id":"2204.13867","date":"2022-04-29","proceeding":"CVPR 2022 1","authors":["Sibo Song","Jianqiang Wan","Zhibo Yang","Jun Tang","Wenqing Cheng","Xiang Bai","Cong Yao"],"abstract":"Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves cross-modal interaction between the two modalities: vision and language, since text is the written form of language. Concretely, we propose to learn contextualized, joint representations through vision-language pre-training, for the sake of enhancing the performance of scene text detectors. Towards this end, we devise a pre-training architecture with an image encoder, a text encoder and a cross-modal encoder, as well as three pretext tasks: image-text contrastive learning (ITC), masked language modeling (MLM) and word-in-image prediction (WIP). The pre-trained model is able to produce more informative representations with richer semantics, which could readily benefit existing scene text detectors (such as EAST and PSENet) in the down-stream text detection task. Extensive experiments on standard benchmarks demonstrate that the proposed paradigm can significantly improve the performance of various representative text detectors, outperforming previous pre-training approaches. The code and pre-trained models will be publicly released.","url_abs":"https://arxiv.org/abs/2204.13867v1","url_pdf":"https://arxiv.org/pdf/2204.13867v1.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":"vision-language-pre-training-for-boosting","repo_url":"https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/VLPT-STD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"vision-language-pre-training-for-boosting","repo_url":"https://github.com/alibabaresearch/advancedliteratemachinery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.13867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13867"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/CVI-SZU/STKM","reach":null}],"summary":{"ran":4,"ran_fixture":1,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":7,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9b153d776f334bc5","entry":"Encoder","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b153d776f334bc5"}},{"code_sha256_prefix":"ddbe5cd199ca5fc2","entry":"Encoder_Layer","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ddbe5cd199ca5fc2"}},{"code_sha256_prefix":"04a294c280204626","entry":"Feed_Forward_Net","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04a294c280204626"}},{"code_sha256_prefix":"1008247d190df035","entry":"Pos_Encoder","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1008247d190df035"}},{"code_sha256_prefix":"ceef05668f1db913","entry":"attention_sdp","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ceef05668f1db913"}},{"code_sha256_prefix":"a6d8c280c44ff126","entry":"Attention_Blosk","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6d8c280c44ff126"}},{"code_sha256_prefix":"515bc2c7a38069cb","entry":"Tensor","repo":"CVI-SZU/STKM","repo_kind":"found_in_text","path":"model/transformers.py","file_url":"https://github.com/CVI-SZU/STKM/blob/HEAD/model/transformers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"515bc2c7a38069cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}