{"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/omni-detr-omni-supervised-object-detection","title":"Omni-DETR: Omni-Supervised Object Detection with Transformers","arxiv_id":"2203.16089","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Pei Wang","Zhaowei Cai","Hao Yang","Gurumurthy Swaminathan","Nuno Vasconcelos","Bernt Schiele","Stefano Soatto"],"abstract":"We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels, by a bipartite matching based filtering mechanism, for the model to learn. In the experiments, Omni-DETR has achieved state-of-the-art results on multiple datasets and settings. And we have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy than the standard complete annotation. These findings could encourage larger object detection datasets with mixture annotations. The code is available at https://github.com/amazon-research/omni-detr.","url_abs":"https://arxiv.org/abs/2203.16089v1","url_pdf":"https://arxiv.org/pdf/2203.16089v1.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":"omni-detr-omni-supervised-object-detection","repo_url":"https://github.com/amazon-research/omni-detr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semi-supervised-object-detection","task_name":"Semi-Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-object-detection-on-coco-1","task":"Semi-Supervised Object Detection","dataset":"COCO 1% labeled data","model":"Omni-DETR","rank_in_archive_order":19,"of":22,"metrics":{"mAP":"18.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-object-detection-on-coco-10","task":"Semi-Supervised Object Detection","dataset":"COCO 10% labeled data","model":"Omni-DETR","rank_in_archive_order":16,"of":27,"metrics":{"mAP":"34.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-object-detection-on-coco-2","task":"Semi-Supervised Object Detection","dataset":"COCO 2% labeled data","model":"Omni-DETR","rank_in_archive_order":14,"of":19,"metrics":{"mAP":"23.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-object-detection-on-coco-5","task":"Semi-Supervised Object Detection","dataset":"COCO 5% labeled data","model":"Omni-DETR","rank_in_archive_order":17,"of":23,"metrics":{"mAP":"30.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.16089","atlas_url":"https://app.syntology.ai/?focus=2203.16089","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}