{"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/pp-yoloe-r-an-efficient-anchor-free-rotated","title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","arxiv_id":"2211.02386","date":"2022-11-04","proceeding":null,"authors":["Xinxin Wang","Guanzhong Wang","Qingqing Dang","Yi Liu","Xiaoguang Hu","dianhai yu"],"abstract":"Arbitrary-oriented object detection is a fundamental task in visual scenes involving aerial images and scene text. In this report, we present PP-YOLOE-R, an efficient anchor-free rotated object detector based on PP-YOLOE. We introduce a bag of useful tricks in PP-YOLOE-R to improve detection precision with marginal extra parameters and computational cost. As a result, PP-YOLOE-R-l and PP-YOLOE-R-x achieve 78.14 and 78.28 mAP respectively on DOTA 1.0 dataset with single-scale training and testing, which outperform almost all other rotated object detectors. With multi-scale training and testing, PP-YOLOE-R-l and PP-YOLOE-R-x further improve the detection precision to 80.02 and 80.73 mAP. In this case, PP-YOLOE-R-x surpasses all anchor-free methods and demonstrates competitive performance to state-of-the-art anchor-based two-stage models. Further, PP-YOLOE-R is deployment friendly and PP-YOLOE-R-s/m/l/x can reach 69.8/55.1/48.3/37.1 FPS respectively on RTX 2080 Ti with TensorRT and FP16-precision. Source code and pre-trained models are available at https://github.com/PaddlePaddle/PaddleDetection, which is powered by https://github.com/PaddlePaddle/Paddle.","url_abs":"https://arxiv.org/abs/2211.02386v1","url_pdf":"https://arxiv.org/pdf/2211.02386v1.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":"pp-yoloe-r-an-efficient-anchor-free-rotated","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":null},{"paper_slug":"pp-yoloe-r-an-efficient-anchor-free-rotated","repo_url":"https://github.com/PaddlePaddle/Paddle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-in-aerial-images","task_name":"Object Detection In Aerial Images"},{"task_slug":"one-stage-anchor-free-oriented-object-1","task_name":"One-stage Anchor-free Oriented Object Detection"},{"task_slug":"oriented-object-detection","task_name":"Oriented Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset":"DOTA","model":"PP-YOLOE-R-x","rank_in_archive_order":16,"of":58,"metrics":{"mAP":"80.73%"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset":"DOTA","model":"PP-YOLOE-R-l","rank_in_archive_order":23,"of":58,"metrics":{"mAP":"80.02%"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset":"DOTA","model":"PP-YOLOE-R-m","rank_in_archive_order":24,"of":58,"metrics":{"mAP":"79.71%"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset":"DOTA","model":"PP-YOLOE-R-s","rank_in_archive_order":27,"of":58,"metrics":{"mAP":"79.42%"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.02386","atlas_url":"https://app.syntology.ai/?focus=2211.02386","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}