{"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/ms-detr-efficient-detr-training-with-mixed","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","arxiv_id":"2401.03989","date":"2024-01-08","proceeding":"CVPR 2024 1","authors":["Chuyang Zhao","Yifan Sun","Wenhao Wang","Qiang Chen","Errui Ding","Yi Yang","Jingdong Wang"],"abstract":"DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one supervision in the original DETR lacks direct supervision for the object detection candidates. We aim at improving the DETR training efficiency by explicitly supervising the candidate generation procedure through mixing one-to-one supervision and one-to-many supervision. Our approach, namely MS-DETR, is simple, and places one-to-many supervision to the object queries of the primary decoder that is used for inference. In comparison to existing DETR variants with one-to-many supervision, such as Group DETR and Hybrid DETR, our approach does not need additional decoder branches or object queries. The object queries of the primary decoder in our approach directly benefit from one-to-many supervision and thus are superior in object candidate prediction. Experimental results show that our approach outperforms related DETR variants, such as DN-DETR, Hybrid DETR, and Group DETR, and the combination with related DETR variants further improves the performance.","url_abs":"https://arxiv.org/abs/2401.03989v1","url_pdf":"https://arxiv.org/pdf/2401.03989v1.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":"ms-detr-efficient-detr-training-with-mixed","repo_url":"https://github.com/atten4vis/ms-detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.03989","atlas_url":"https://app.syntology.ai/?focus=2401.03989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03989"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/atten4vis/ms-detr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Atten4Vis/MS-DETR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":2,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f31a58bf6457ced5","entry":"convert_to_xywh","repo":"atten4vis/ms-detr","repo_kind":"official","path":"datasets/coco_eval.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/datasets/coco_eval.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f31a58bf6457ced5"}},{"code_sha256_prefix":"ac8fe530cdad4d8c","entry":"dice_loss","repo":"atten4vis/ms-detr","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac8fe530cdad4d8c"}},{"code_sha256_prefix":"fe0ddcc2d420c9a0","entry":"evaluate","repo":"atten4vis/ms-detr","repo_kind":"official","path":"datasets/coco_eval.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/datasets/coco_eval.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe0ddcc2d420c9a0"}},{"code_sha256_prefix":"d28e238107e0aa1b","entry":"nonzero_tuple","repo":"atten4vis/ms-detr","repo_kind":"official","path":"models/matcher_o2m.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/matcher_o2m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d28e238107e0aa1b"}},{"code_sha256_prefix":"0860cd732b6fa70d","entry":"sample_topk_per_gt","repo":"atten4vis/ms-detr","repo_kind":"official","path":"models/matcher_o2m.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/matcher_o2m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0860cd732b6fa70d"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"atten4vis/ms-detr","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"19a04bf3d341cedb","entry":"subsample_labels","repo":"atten4vis/ms-detr","repo_kind":"official","path":"models/matcher_o2m.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/matcher_o2m.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19a04bf3d341cedb"}},{"code_sha256_prefix":"e4520db8ba29f9f4","entry":"DeformableDETR","repo":"Atten4Vis/MS-DETR","repo_kind":"official","path":"models/deformable_detr.py","file_url":"https://github.com/Atten4Vis/MS-DETR/blob/HEAD/models/deformable_detr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4520db8ba29f9f4"}},{"code_sha256_prefix":"3e5d34f155e97585","entry":"measure_average_inference_time","repo":"atten4vis/ms-detr","repo_kind":"official","path":"benchmark.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/benchmark.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e5d34f155e97585"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}