{"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/r-fcn-3000-at-30fps-decoupling-detection-and","title":"R-FCN-3000 at 30fps: Decoupling Detection and Classification","arxiv_id":"1712.01802","date":"2017-12-05","proceeding":"CVPR 2018 6","authors":["Bharat Singh","Hengduo Li","Abhishek Sharma","Larry S. Davis"],"abstract":"We present R-FCN-3000, a large-scale real-time object detector in which\nobjectness detection and classification are decoupled. To obtain the detection\nscore for an RoI, we multiply the objectness score with the fine-grained\nclassification score. Our approach is a modification of the R-FCN architecture\nin which position-sensitive filters are shared across different object classes\nfor performing localization. For fine-grained classification, these\nposition-sensitive filters are not needed. R-FCN-3000 obtains an mAP of 34.9%\non the ImageNet detection dataset and outperforms YOLO-9000 by 18% while\nprocessing 30 images per second. We also show that the objectness learned by\nR-FCN-3000 generalizes to novel classes and the performance increases with the\nnumber of training object classes - supporting the hypothesis that it is\npossible to learn a universal objectness detector. Code will be made available.","url_abs":"http://arxiv.org/abs/1712.01802v1","url_pdf":"http://arxiv.org/pdf/1712.01802v1.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":"r-fcn-3000-at-30fps-decoupling-detection-and","repo_url":"https://github.com/MahyarNajibi/SNIPER","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"r-fcn-3000-at-30fps-decoupling-detection-and","repo_url":"https://github.com/starimpact/arm_SNIPER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"position-sensitive-roi-pooling","method_name":"Position-Sensitive RoI Pooling"},{"method_slug":"r-fcn","method_name":"R-FCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.01802","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}