{"url":"/sota/visual-place-recognition-on-pittsburgh-250k","task":{"name":"Visual Place Recognition","url":"/task/visual-place-recognition","note":null},"dataset":{"name":"Pittsburgh-250k-test","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Visual Place Recognition** is the task of matching a view of a place with a different view of the same place taken at a different time.\r\n\r\n<span class=\"description-source\">Source: [Visual place recognition using landmark distribution descriptors ](https://arxiv.org/abs/1608.04274)</span>\r\n\r\nImage credit: [Visual place recognition using landmark distribution descriptors](https://arxiv.org/pdf/1608.04274.pdf)","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":["Recall@1","Recall@10","Recall@5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Recall@1":"higher","Recall@10":"higher","Recall@5":"higher"}},"counts":{"rows":13,"rows_with_code":12,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"FoL","metrics":{"Recall@1":"97.0","Recall@10":"99.2","Recall@5":"99.5"},"uses_additional_data":false,"paper_date":"2025-04-14","paper":"/paper/focus-on-local-finding-reliable-1","paper_url":"https://arxiv.org/abs/2504.09881v1","paper_title":"Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition","code":"https://github.com/chenshunpeng/FoL","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"BoQ","metrics":{"Recall@1":"96.6","Recall@10":"99.5","Recall@5":"99.1"},"uses_additional_data":false,"paper_date":"2024-05-12","paper":"/paper/boq-a-place-is-worth-a-bag-of-learnable","paper_url":"https://arxiv.org/abs/2405.07364v3","paper_title":"BoQ: A Place is Worth a Bag of Learnable Queries","code":"https://github.com/amaralibey/bag-of-queries","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"QAA-DINOv2-B-8192","metrics":{"Recall@1":"96.6"},"uses_additional_data":true,"paper_date":"2025-07-04","paper":"/paper/query-based-adaptive-aggregation-for-multi","paper_url":"https://arxiv.org/abs/2507.03831v1","paper_title":"Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"FoL-global","metrics":{"Recall@1":"96.5","Recall@10":"99.1","Recall@5":"99.5"},"uses_additional_data":false,"paper_date":"2025-04-14","paper":"/paper/focus-on-local-finding-reliable-1","paper_url":"https://arxiv.org/abs/2504.09881v1","paper_title":"Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition","code":"https://github.com/chenshunpeng/FoL","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SelaVPR","metrics":{"Recall@1":"95.7","Recall@10":"98.8","Recall@5":"99.2"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/towards-seamless-adaptation-of-pre-trained","paper_url":"https://arxiv.org/abs/2402.14505v3","paper_title":"Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition","code":"https://github.com/Lu-Feng/SelaVPR","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DINOv2 SALAD","metrics":{"Recall@1":"95.1","Recall@10":"99.1","Recall@5":"98.5"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/optimal-transport-aggregation-for-visual","paper_url":"https://arxiv.org/abs/2311.15937v2","paper_title":"Optimal Transport Aggregation for Visual Place Recognition","code":"https://github.com/serizba/salad","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":7,"model":"BoQ (ResNet-50)","metrics":{"Recall@1":"95","Recall@10":"99.1","Recall@5":"98.5"},"uses_additional_data":false,"paper_date":"2024-05-12","paper":"/paper/boq-a-place-is-worth-a-bag-of-learnable","paper_url":"https://arxiv.org/abs/2405.07364v3","paper_title":"BoQ: A Place is Worth a Bag of Learnable Queries","code":"https://github.com/amaralibey/bag-of-queries","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"MixVPR","metrics":{"Recall@1":"94.6","Recall@10":"99.0","Recall@5":"98.3"},"uses_additional_data":false,"paper_date":"2023-03-03","paper":"/paper/mixvpr-feature-mixing-for-visual-place","paper_url":"https://arxiv.org/abs/2303.02190v1","paper_title":"MixVPR: Feature Mixing for Visual Place Recognition","code":"https://github.com/amaralibey/mixvpr","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"EigenPlaces","metrics":{"Recall@1":"94.1"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/eigenplaces-training-viewpoint-robust-models","paper_url":"https://arxiv.org/abs/2308.10832v1","paper_title":"EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition","code":"https://github.com/stschubert/vpr_tutorial","n_code_links":4,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"Conv-AP","metrics":{"Recall@1":"92.4","Recall@10":"98.6","Recall@5":"97.6"},"uses_additional_data":false,"paper_date":"2022-10-19","paper":"/paper/gsv-cities-toward-appropriate-supervised","paper_url":"https://arxiv.org/abs/2210.10239v1","paper_title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","code":"https://github.com/amaralibey/gsv-cities","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"ProGEO","metrics":{"Recall@1":"92.2","Recall@5":"97.7"},"uses_additional_data":true,"paper_date":"2024-06-04","paper":"/paper/progeo-generating-prompts-through-image-text","paper_url":"https://arxiv.org/abs/2406.01906v1","paper_title":"ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization","code":"https://github.com/chain-mao/progeo","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"NetVLAD (with GPM)","metrics":{"Recall@1":"91.5","Recall@10":"98.1","Recall@5":"97.2"},"uses_additional_data":true,"paper_date":"2023-02-28","paper":"/paper/global-proxy-based-hard-mining-for-visual","paper_url":"https://arxiv.org/abs/2302.14217v1","paper_title":"Global Proxy-based Hard Mining for Visual Place Recognition","code":"https://github.com/amaralibey/gpm","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"CosPlace","metrics":{"Recall@1":"91.5","Recall@10":"97.9","Recall@5":"96.9"},"uses_additional_data":true,"paper_date":"2022-04-05","paper":"/paper/rethinking-visual-geo-localization-for-large","paper_url":"https://arxiv.org/abs/2204.02287v2","paper_title":"Rethinking Visual Geo-localization for Large-Scale Applications","code":"https://github.com/gmberton/cosplace","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":2}}],"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":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":24,"n_unverified":11,"n_samples":35,"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":29,"n_unverified":11,"n_samples":40,"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"}}}