{"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/probabilistic-two-stage-detection","title":"Probabilistic two-stage detection","arxiv_id":"2103.07461","date":"2021-03-12","proceeding":null,"authors":["Xingyi Zhou","Vladlen Koltun","Philipp Krähenbühl"],"abstract":"We develop a probabilistic interpretation of two-stage object detection. We show that this probabilistic interpretation motivates a number of common empirical training practices. It also suggests changes to two-stage detection pipelines. Specifically, the first stage should infer proper object-vs-background likelihoods, which should then inform the overall score of the detector. A standard region proposal network (RPN) cannot infer this likelihood sufficiently well, but many one-stage detectors can. We show how to build a probabilistic two-stage detector from any state-of-the-art one-stage detector. The resulting detectors are faster and more accurate than both their one- and two-stage precursors. Our detector achieves 56.4 mAP on COCO test-dev with single-scale testing, outperforming all published results. Using a lightweight backbone, our detector achieves 49.2 mAP on COCO at 33 fps on a Titan Xp, outperforming the popular YOLOv4 model.","url_abs":"https://arxiv.org/abs/2103.07461v1","url_pdf":"https://arxiv.org/pdf/2103.07461v1.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":"probabilistic-two-stage-detection","repo_url":"https://github.com/xingyizhou/CenterNet2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"probabilistic-two-stage-detection","repo_url":"https://github.com/aim-uofa/DiverGen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"probabilistic-two-stage-detection","repo_url":"https://github.com/smart-car-lab/Centernet2-mmdetction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale)","rank_in_archive_order":42,"of":225,"metrics":{"AP50":"74.0","AP75":"61.6","APL":"68.6","APM":"59.7","APS":"38.7","box mAP":"56.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"CenterNet2\n(R2-101-DCN)","rank_in_archive_order":20,"of":45,"metrics":{"Average mAP":"29.5","Effective Robustness":"4.29"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.07461","atlas_url":"https://app.syntology.ai/?focus=2103.07461","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}