{"url":"/sota/object-detection-on-lvis-v1-0-val","task":{"name":"Object Detection","url":"/task/object-detection","note":null},"dataset":{"name":"LVIS v1.0 val","url":"/dataset/lvis"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["box AP","box APr"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"box AP":"higher","box APr":null}},"counts":{"rows":15,"rows_with_code":15,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"Co-DETR (single-scale)","metrics":{"box AP":"68.0"},"uses_additional_data":true,"paper_date":"2022-11-22","paper":"/paper/detrs-with-collaborative-hybrid-assignments","paper_url":"https://arxiv.org/abs/2211.12860v5","paper_title":"DETRs with Collaborative Hybrid Assignments Training","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Grounding DINO 1.5 Pro","metrics":{"box AP":"63.5","box APr":"64.0"},"uses_additional_data":true,"paper_date":"2024-05-16","paper":"/paper/grounding-dino-1-5-advance-the-edge-of-open","paper_url":"https://arxiv.org/abs/2405.10300v2","paper_title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","code":"https://github.com/mit-han-lab/efficientvit","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"InternImage-H","metrics":{"box AP":"63.2"},"uses_additional_data":true,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"EVA","metrics":{"box AP":"62.2","box APr":"55.1"},"uses_additional_data":true,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"RichSem (Focal-H + ImageNet as weakly-supervised extra data)","metrics":{"box AP":"61.2","box APr":"61.2"},"uses_additional_data":true,"paper_date":"2023-10-18","paper":"/paper/learning-from-rich-semantics-and-coarse","paper_url":"https://arxiv.org/abs/2310.12152v1","paper_title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","code":"https://github.com/MengLcool/RichSem","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":6,"model":"GLEE-Pro","metrics":{"box AP":"55.7"},"uses_additional_data":true,"paper_date":"2023-12-14","paper":"/paper/general-object-foundation-model-for-images","paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","code":"https://github.com/FoundationVision/GLEE","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ViTDet-H","metrics":{"box AP":"53.4"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SimLTD w/MixPL (Swin-L + COCO unlabeled images)","metrics":{"box AP":"51.5"},"uses_additional_data":true,"paper_date":"2024-12-28","paper":"/paper/simltd-simple-supervised-and-semi-supervised","paper_url":"https://arxiv.org/abs/2412.20047v1","paper_title":"SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection","code":"https://github.com/lexisnexis-risk-open-source/simltd","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"DiverGen (Swin-L)","metrics":{"box AP":"51.2","box APr":"50.1"},"uses_additional_data":false,"paper_date":"2024-05-16","paper":"/paper/divergen-improving-instance-segmentation-by","paper_url":"https://arxiv.org/abs/2405.10185v1","paper_title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","code":"https://github.com/aim-uofa/DiverGen","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"ViTDet-L","metrics":{"box AP":"51.2"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)","metrics":{"box AP":"50.9","box APr":"48.7"},"uses_additional_data":false,"paper_date":"2022-12-07","paper":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip","paper_url":"https://arxiv.org/abs/2212.03863v2","paper_title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","code":"https://github.com/aim-uofa/DiverGen","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":12,"model":"SimLTD Fully Supervised (Swin-L)","metrics":{"box AP":"49.8","box APr":"42.4"},"uses_additional_data":false,"paper_date":"2024-12-28","paper":"/paper/simltd-simple-supervised-and-semi-supervised","paper_url":"https://arxiv.org/abs/2412.20047v1","paper_title":"SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection","code":"https://github.com/lexisnexis-risk-open-source/simltd","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))","metrics":{"box AP":"41.6"},"uses_additional_data":false,"paper_date":"2020-12-13","paper":"/paper/simple-copy-paste-is-a-strong-data","paper_url":"https://arxiv.org/abs/2012.07177v2","paper_title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"R101-MaskRCNN-LOCE","metrics":{"box AP":"29"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/exploring-classification-equilibrium-in-long","paper_url":"https://arxiv.org/abs/2108.07507v2","paper_title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","code":"https://github.com/fcjian/loce","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"R50-MaskRCNN-LOCE","metrics":{"box AP":"27.4"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/exploring-classification-equilibrium-in-long","paper_url":"https://arxiv.org/abs/2108.07507v2","paper_title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","code":"https://github.com/fcjian/loce","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":12,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":28,"n_unverified":17,"n_samples":45,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":32,"n_unverified":19,"n_samples":51,"n_pointer_only_licence":10,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}