{"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/mask-r-cnn-with-pyramid-attention-network-for","title":"Mask R-CNN with Pyramid Attention Network for Scene Text Detection","arxiv_id":"1811.09058","date":"2018-11-22","proceeding":null,"authors":["Zhida Huang","Zhuoyao Zhong","Lei Sun","Qiang Huo"],"abstract":"In this paper, we present a new Mask R-CNN based text detection approach\nwhich can robustly detect multi-oriented and curved text from natural scene\nimages in a unified manner. To enhance the feature representation ability of\nMask R-CNN for text detection tasks, we propose to use the Pyramid Attention\nNetwork (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate\nthat PAN can suppress false alarms caused by text-like backgrounds more\neffectively. Our proposed approach has achieved superior performance on both\nmulti-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500) text\ndetection benchmark tasks by only using single-scale and single-model testing.","url_abs":"http://arxiv.org/abs/1811.09058v1","url_pdf":"http://arxiv.org/pdf/1811.09058v1.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":[],"tasks":[{"task_slug":"curved-text-detection","task_name":"Curved Text Detection"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"PAN","rank_in_archive_order":22,"of":43,"metrics":{"F-Measure":"85.9","Precision":"90.8","Recall":"81.5"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2017-mlt-1","task":"Scene Text Detection","dataset":"ICDAR 2017 MLT","model":"PAN","rank_in_archive_order":9,"of":14,"metrics":{"F-Measure":"74.3%","Precision":"80","Recall":"69.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","task":"Scene Text Detection","dataset":"SCUT-CTW1500","model":"PAN","rank_in_archive_order":6,"of":17,"metrics":{"F-Measure":"85","FPS":"65.2","Precision":"86.8","Recall":"83.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}