{"url":"/dataset/vehicleid","name":"VehicleID","full_name":"PKU VehicleID","description_markdown":"The “**VehicleID**” dataset contains CARS captured during the daytime by multiple real-world surveillance cameras distributed in a small city in China. There are 26,267 vehicles (221,763 images in total) in the entire dataset. Each image is attached with an id label corresponding to its identity in real world. In addition, the dataset contains manually labelled 10319 vehicles (90196 images in total) of their vehicle model information(i.e.“MINI-cooper”, “Audi A6L” and “BWM 1 Series”).\r\n\r\nSource: [https://www.pkuml.org/resources/pku-vehicleid.html](https://www.pkuml.org/resources/pku-vehicleid.html)\r\nImage Source: [https://www.pkuml.org/resources/pku-vehicleid.html](https://www.pkuml.org/resources/pku-vehicleid.html)","description_withheld":null,"homepage":"https://www.pkuml.org/resources/pku-vehicleid.html","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-relative-distance-learning-tell-the","title":"Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles","first_author":"Hongye Liu","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://www.pkuml.org/resources/pku-vehicleid.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Vehicle Re-Identification","url":"/task/vehicle-re-identification","datasets_with_task":"/datasets/task/vehicle-re-identification"}],"languages":[],"variants":["Veri-776 to VehicleID Large","Veri-776 to VehicleID Medium","Veri-776 to VehicleID Small","VehicleID to VeRi-776 ","VehicleID","VehicleID Small","VehicleID Medium","VehicleID Large"],"data_loaders":[{"repo":"https://github.com/michuanhaohao/reid-strong-baseline","url":"https://github.com/michuanhaohao/reid-strong-baseline","frameworks":["pytorch"]}],"num_papers_in_archive":134,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid","task":"Unsupervised Domain Adaptation","dataset_variant":"VehicleID to VeRi-776","rows":14,"metrics":["mAP","Rank-1","Rank-5","Rank-10"],"first_row_in_archive_order":{"model":"CORE-ReID V2","paper":"/paper/core-reid-v2-advancing-the-domain-adaptation","metrics":{"Rank-1":"80.15","Rank-10":"90.29","Rank-5":"89.05","mAP":"49.50"},"code_links":[{"title":"TrinhQuocNguyen/CORE-ReID-v2","url":"https://github.com/TrinhQuocNguyen/CORE-ReID-v2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to-1","task":"Unsupervised Domain Adaptation","dataset_variant":"Veri-776 to VehicleID Medium","rows":13,"metrics":["mAP","R-1","R-5","R-10"],"first_row_in_archive_order":{"model":"CORE-ReID V2","paper":"/paper/core-reid-v2-advancing-the-domain-adaptation","metrics":{"R-1":"53.49","R-10":"81.85","R-5":"74.36","mAP":"63.02"},"code_links":[{"title":"TrinhQuocNguyen/CORE-ReID-v2","url":"https://github.com/TrinhQuocNguyen/CORE-ReID-v2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to-2","task":"Unsupervised Domain Adaptation","dataset_variant":"Veri-776 to VehicleID Large","rows":13,"metrics":["mAP","R-1","R-5","R-10"],"first_row_in_archive_order":{"model":"CORE-ReID V2","paper":"/paper/core-reid-v2-advancing-the-domain-adaptation","metrics":{"R-1":"48.62","R-10":"77.11","R-5":"68.30","mAP":"57.99"},"code_links":[{"title":"TrinhQuocNguyen/CORE-ReID-v2","url":"https://github.com/TrinhQuocNguyen/CORE-ReID-v2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-small","task":"Vehicle Re-Identification","dataset_variant":"VehicleID Small","rows":13,"metrics":["Rank-1","Rank-5","Rank1","Rank5","mAP"],"first_row_in_archive_order":{"model":"Recall@k Surrogate loss (ViT-B/16)","paper":"/paper/recall-k-surrogate-loss-with-large-batches","metrics":{"Rank-1":"96.2","Rank-5":"98.0"},"code_links":[{"title":"yash0307/RecallatK_surrogate","url":"https://github.com/yash0307/RecallatK_surrogate"},{"title":"yash0307/recallatk","url":"https://github.com/yash0307/recallatk"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-large","task":"Vehicle Re-Identification","dataset_variant":"VehicleID Large","rows":10,"metrics":["Rank-1","Rank-5","Rank1","Rank5","mAP"],"first_row_in_archive_order":{"model":"Recall@k Surrogate loss (ViT-B/16)","paper":"/paper/recall-k-surrogate-loss-with-large-batches","metrics":{"Rank-1":"94.7","Rank-5":"97.1"},"code_links":[{"title":"yash0307/RecallatK_surrogate","url":"https://github.com/yash0307/RecallatK_surrogate"},{"title":"yash0307/recallatk","url":"https://github.com/yash0307/recallatk"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-medium","task":"Vehicle Re-Identification","dataset_variant":"VehicleID Medium","rows":9,"metrics":["Rank-1","Rank-5","Rank1","Rank5","mAP"],"first_row_in_archive_order":{"model":"Recall@k Surrogate loss (ViT-B/16)","paper":"/paper/recall-k-surrogate-loss-with-large-batches","metrics":{"Rank-1":"95.2","Rank-5":"97.2"},"code_links":[{"title":"yash0307/RecallatK_surrogate","url":"https://github.com/yash0307/RecallatK_surrogate"},{"title":"yash0307/recallatk","url":"https://github.com/yash0307/recallatk"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to","task":"Unsupervised Domain Adaptation","dataset_variant":"Veri-776 to VehicleID Small","rows":8,"metrics":[" mAP","R-1","R-5","R-10"],"first_row_in_archive_order":{"model":"CORE-ReID V2","paper":"/paper/core-reid-v2-advancing-the-domain-adaptation","metrics":{" mAP":"67.04","R-1":"58.32","R-10":"84.51","R-5":"76.51"},"code_links":[{"title":"TrinhQuocNguyen/CORE-ReID-v2","url":"https://github.com/TrinhQuocNguyen/CORE-ReID-v2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid","task":"Vehicle Re-Identification","dataset_variant":"VehicleID","rows":1,"metrics":["Rank1"],"first_row_in_archive_order":{"model":"VehicleNet","paper":"/paper/vehiclenet-learning-robust-visual","metrics":{"Rank1":"83.64"},"code_links":[{"title":"layumi/Person_reID_baseline_pytorch","url":"https://github.com/layumi/Person_reID_baseline_pytorch"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/VehicleNet"},{"title":"totoroKalic/vehiclenet-mindspore","url":"https://github.com/totoroKalic/vehiclenet-mindspore"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/core-reid-v2-advancing-the-domain-adaptation","title":"CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion","date":"2025-07-04","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-multi-granularity-representation","title":"Revisiting Multi-Granularity Representation via Group Contrastive Learning for Unsupervised Vehicle Re-identification","date":"2024-10-29","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/multimodality-adaptive-transformer-and-mutual","title":"Multimodality Adaptive Transformer and Mutual Learning for Unsupervised Domain Adaptation Vehicle Re-Identification","date":"2024-09-17","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/strength-in-diversity-multi-branch","title":"Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification","date":"2023-10-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-vehicle-re-identification-based","title":"Unsupervised Vehicle Re-Identification Based on Cross-Style Semi-Supervised Pre-Training and Feature Cross-Division","date":"2023-07-03","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/image-to-image-domain-adaptation-for-vehicle","title":"Image-to-image domain adaptation for vehicle re-identification","date":"2023-03-30","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/msinet-twins-contrastive-search-of-multi","title":"MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID","date":"2023-03-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clip-reid-exploiting-vision-language-model","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","date":"2022-11-25","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/progressive-learning-with-multi-scale","title":"Progressive learning with multi-scale attention network for cross-domain vehicle re-identification","date":"2021-11-19","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/relation-preserving-triplet-mining-for","title":"Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems","date":"2021-10-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/recall-k-surrogate-loss-with-large-batches","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","date":"2021-08-25","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/counterfactual-attention-learning-for-fine","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","date":"2021-08-19","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/git-graph-interactive-transformer-for-vehicle","title":"GiT: Graph Interactive Transformer for Vehicle Re-identification","date":"2021-07-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-multiple-semantic-knowledge-for","title":"Learning Multiple Semantic Knowledge For Cross-Domain Unsupervised Vehicle Re-Identification","date":"2021-07-05","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-ranking-based-loss-functions-only","title":"Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough","date":"2021-02-09","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/attributenet-attribute-enhanced-vehicle-re","title":"AttributeNet: Attribute Enhanced Vehicle Re-Identification","date":"2021-02-07","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/vehiclenet-learning-robust-feature","title":"VehicleNet: Learning Robust Feature Representation for Vehicle Re-identification","date":"2020-08-07","rows_on_this_dataset":3,"code_links":7,"syntology":null},{"paper":"/paper/smooth-ap-smoothing-the-path-towards-large","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","date":"2020-07-23","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-vehicle-re-identification-with","title":"Unsupervised Vehicle Re-identification with Progressive Adaptation","date":"2020-06-20","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/self-paced-contrastive-learning-with-hybrid","title":"Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID","date":"2020-06-04","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-spatial-significance-via-hybrid","title":"Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification","date":"2020-05-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vehiclenet-learning-robust-visual","title":"VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification","date":"2020-04-14","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mutual-mean-teaching-pseudo-label-refinery-1","title":"Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification","date":"2020-01-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/invariance-matters-exemplar-memory-for-domain","title":"Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification","date":"2019-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vehicle-re-identification-using-quadruple","title":"Vehicle Re-identification Using Quadruple Directional Deep Learning Features","date":"2018-11-13","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/unsupervised-domain-adaptive-re","title":"Unsupervised Domain Adaptive Re-Identification: Theory and Practice","date":"2018-07-30","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-image-domain-adaptation-with-preserved","title":"Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification","date":"2017-11-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsupervised-person-re-identification","title":"Unsupervised Person Re-identification: Clustering and Fine-tuning","date":"2017-05-30","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/a-deep-learning-based-approach-to-progressive","title":"A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance","date":"2016-09-17","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/deep-relative-distance-learning-tell-the","title":"Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles","date":"2016-06-01","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":7,"samples_harvested":50,"samples_ran":21,"samples_unverified":29,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}