{"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/bridging-synthetic-and-real-worlds-for-pre","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","arxiv_id":"2312.05286","date":"2023-12-08","proceeding":null,"authors":["Tongkun Guan","Wei Shen","Xue Yang","Xuehui Wang","Xiaokang Yang"],"abstract":"Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-training text detectors. However, a synth-to-real domain gap emerges, further limiting the performance of text detectors. Differently, in this work, we propose FreeReal, a real-domain-aligned pre-training paradigm that enables the complementary strengths of both LSD and unlabeled real data (URD). Specifically, to bridge real and synthetic worlds for pre-training, a glyph-based mixing mechanism (GlyphMix) is tailored for text images.GlyphMix delineates the character structures of synthetic images and embeds them as graffiti-like units onto real images. Without introducing real domain drift, GlyphMix freely yields real-world images with annotations derived from synthetic labels. Furthermore, when given free fine-grained synthetic labels, GlyphMix can effectively bridge the linguistic domain gap stemming from English-dominated LSD to URD in various languages. Without bells and whistles, FreeReal achieves average gains of 1.97%, 3.90%, 3.85%, and 4.56% in improving the performance of FCENet, PSENet, PANet, and DBNet methods, respectively, consistently outperforming previous pre-training methods by a substantial margin across four public datasets. Code is available at https://github.com/SJTU-DeepVisionLab/FreeReal.","url_abs":"https://arxiv.org/abs/2312.05286v3","url_pdf":"https://arxiv.org/pdf/2312.05286v3.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":"bridging-synthetic-and-real-worlds-for-pre","repo_url":"https://github.com/sjtu-deepvisionlab/freereal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adaptive-feature-pooling","method_name":"Adaptive Feature Pooling"},{"method_slug":"bottom-up-path-augmentation","method_name":"Bottom-up Path Augmentation"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"pafpn","method_name":"PAFPN"},{"method_slug":"panet","method_name":"PANet"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"roi-align","method_name":"RoIAlign"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.05286","atlas_url":"https://app.syntology.ai/?focus=2312.05286","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}