{"url":"/sota/vehicle-re-identification-on-vehicleid-small","task":{"name":"Vehicle Re-Identification","url":"/task/vehicle-re-identification","note":null},"dataset":{"name":"VehicleID Small","url":"/dataset/vehicleid"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Vehicle re-identification is the task of identifying the same vehicle across multiple cameras.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras](https://github.com/icarofua/siamese-two-stream) )</span>","description_from":"task","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":["Rank-1","Rank-5","Rank1","Rank5","mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Rank-1":null,"Rank-5":null,"Rank1":null,"Rank5":null,"mAP":"higher"}},"counts":{"rows":13,"rows_with_code":10,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Recall@k Surrogate loss (ViT-B/16)","metrics":{"Rank-1":"96.2","Rank-5":"98.0"},"uses_additional_data":false,"paper_date":"2021-08-25","paper":"/paper/recall-k-surrogate-loss-with-large-batches","paper_url":"https://arxiv.org/abs/2108.11179v2","paper_title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","code":"https://github.com/yash0307/RecallatK_surrogate","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Recall@k Surrogate loss (ResNet-50)","metrics":{"Rank-1":"95.7","Rank-5":"97.9"},"uses_additional_data":false,"paper_date":"2021-08-25","paper":"/paper/recall-k-surrogate-loss-with-large-batches","paper_url":"https://arxiv.org/abs/2108.11179v2","paper_title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","code":"https://github.com/yash0307/RecallatK_surrogate","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PNP Loss","metrics":{"Rank-1":"95.5","Rank-5":"97.8"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/rethinking-ranking-based-loss-functions-only","paper_url":"https://arxiv.org/abs/2102.04640v4","paper_title":"Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough","code":"https://github.com/interestingzhuo/pnploss","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"RPTM","metrics":{"Rank-1":"95.5","Rank-5":"97.4","mAP":"84.8"},"uses_additional_data":false,"paper_date":"2021-10-15","paper":"/paper/relation-preserving-triplet-mining-for","paper_url":"https://arxiv.org/abs/2110.07933v2","paper_title":"Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems","code":"https://github.com/adhirajghosh/rptm_reid","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Smooth-AP","metrics":{"Rank-1":"94.9","Rank-5":"97.6"},"uses_additional_data":false,"paper_date":"2020-07-23","paper":"/paper/smooth-ap-smoothing-the-path-towards-large","paper_url":"https://arxiv.org/abs/2007.12163v2","paper_title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","code":"https://github.com/Andrew-Brown1/Smooth_AP","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MBR-4B (without RK)","metrics":{"Rank-1":"88.3","mAP":"92.5"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/strength-in-diversity-multi-branch","paper_url":"https://arxiv.org/abs/2310.01129v1","paper_title":"Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification","code":"https://github.com/videturfortuna/vehicle_reid_itsc2023","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"ANet","metrics":{"Rank-1":"87.9","Rank-5":"97.8","Rank1":"87.9","Rank5":"97.8"},"uses_additional_data":false,"paper_date":"2021-02-07","paper":"/paper/attributenet-attribute-enhanced-vehicle-re","paper_url":"https://arxiv.org/abs/2102.03898v2","paper_title":"AttributeNet: Attribute Enhanced Vehicle Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"CLIP-ReID (without re-ranking)","metrics":{"Rank-1":"85.5","Rank-5":"97.2"},"uses_additional_data":false,"paper_date":"2022-11-25","paper":"/paper/clip-reid-exploiting-vision-language-model","paper_url":"https://arxiv.org/abs/2211.13977v4","paper_title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"vehiclenet","metrics":{"Rank-1":"83.64"},"uses_additional_data":true,"paper_date":"2020-08-07","paper":"/paper/vehiclenet-learning-robust-feature","paper_url":"https://arxiv.org/abs/2004.06305","paper_title":"VehicleNet: Learning Robust Feature Representation for Vehicle Re-identification","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":7,"syntology":null},{"rank_in_archive_order":10,"model":"CAL","metrics":{"Rank-1":"82.5","mAP":"87.8"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GiT","metrics":{"Rank1":"84.65","mAP":"90.12"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/git-graph-interactive-transformer-for-vehicle","paper_url":"https://arxiv.org/abs/2107.05475v3","paper_title":"GiT: Graph Interactive Transformer for Vehicle Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"HPGN","metrics":{"Rank1":"83.91","mAP":"89.6"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/exploring-spatial-significance-via-hybrid","paper_url":"https://arxiv.org/abs/2005.14684v2","paper_title":"Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification","code":"https://github.com/muzishen/HPGN","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"QD-DLF","metrics":{"mAP":"76.54"},"uses_additional_data":false,"paper_date":"2018-11-13","paper":"/paper/vehicle-re-identification-using-quadruple","paper_url":"http://arxiv.org/abs/1811.05163v1","paper_title":"Vehicle Re-identification Using Quadruple Directional Deep Learning Features","code":null,"n_code_links":0,"syntology":null}],"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":4,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":14,"n_samples":24,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":25,"n_samples":35,"n_pointer_only_licence":0,"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"}}}