{"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/cstr-a-classification-perspective-on-scene","title":"Revisiting Classification Perspective on Scene Text Recognition","arxiv_id":"2102.10884","date":"2021-02-22","proceeding":null,"authors":["Hongxiang Cai","Jun Sun","Yichao Xiong"],"abstract":"The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter requires character level annotations that is expensive. In this paper, we revisit classification perspective that models scene text recognition as an image classification problem. Classification perspective has a simple pipeline and only needs word level annotations. We revive classification perspective by devising a scene text recognition model named as CSTR, which performs as well as methods from other perspectives. The CSTR model consists of CPNet (classification perspective network) and SPPN (separated conv with global average pooling prediction network). CSTR is as simple as image classification model like ResNet \\cite{he2016deep} which makes it easy to implement and deploy. We demonstrate the effectiveness of the classification perspective on scene text recognition with extensive experiments. Futhermore, CSTR achieves nearly state-of-the-art performance on six public benchmarks including regular text, irregular text. The code will be available at https://github.com/Media-Smart/vedastr.","url_abs":"https://arxiv.org/abs/2102.10884v3","url_pdf":"https://arxiv.org/pdf/2102.10884v3.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":"cstr-a-classification-perspective-on-scene","repo_url":"https://github.com/Media-Smart/vedastr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-icdar-2003","task":"Scene Text Recognition","dataset":"ICDAR 2003","model":"CSTR","rank_in_archive_order":6,"of":12,"metrics":{"Accuracy":"94.8"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"CSTR","rank_in_archive_order":26,"of":38,"metrics":{"Accuracy":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"CSTR","rank_in_archive_order":16,"of":27,"metrics":{"Accuracy":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"CSTR","rank_in_archive_order":24,"of":37,"metrics":{"Accuracy":"90.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.10884","atlas_url":"https://app.syntology.ai/?focus=2102.10884","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}