{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mixvpr-feature-mixing-for-visual-place","title":"MixVPR: Feature Mixing for Visual Place Recognition","arxiv_id":"2303.02190","date":"2023-03-03","proceeding":null,"authors":["Amar Ali-bey","Brahim Chaib-Draa","Philippe Giguère"],"abstract":"Visual Place Recognition (VPR) is a crucial part of mobile robotics and autonomous driving as well as other computer vision tasks. It refers to the process of identifying a place depicted in a query image using only computer vision. At large scale, repetitive structures, weather and illumination changes pose a real challenge, as appearances can drastically change over time. Along with tackling these challenges, an efficient VPR technique must also be practical in real-world scenarios where latency matters. To address this, we introduce MixVPR, a new holistic feature aggregation technique that takes feature maps from pre-trained backbones as a set of global features. Then, it incorporates a global relationship between elements in each feature map in a cascade of feature mixing, eliminating the need for local or pyramidal aggregation as done in NetVLAD or TransVPR. We demonstrate the effectiveness of our technique through extensive experiments on multiple large-scale benchmarks. Our method outperforms all existing techniques by a large margin while having less than half the number of parameters compared to CosPlace and NetVLAD. We achieve a new all-time high recall@1 score of 94.6% on Pitts250k-test, 88.0% on MapillarySLS, and more importantly, 58.4% on Nordland. Finally, our method outperforms two-stage retrieval techniques such as Patch-NetVLAD, TransVPR and SuperGLUE all while being orders of magnitude faster. Our code and trained models are available at https://github.com/amaralibey/MixVPR.","url_abs":"https://arxiv.org/abs/2303.02190v1","url_pdf":"https://arxiv.org/pdf/2303.02190v1.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":"mixvpr-feature-mixing-for-visual-place","repo_url":"https://github.com/amaralibey/mixvpr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-place-recognition-on-17-places","task":"Visual Place Recognition","dataset":"17 Places","model":"MixVPR","rank_in_archive_order":3,"of":8,"metrics":{"Recall@1":"63.79"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-baidu-mall","task":"Visual Place Recognition","dataset":"Baidu Mall","model":"MixVPR","rank_in_archive_order":3,"of":8,"metrics":{"Recall@1":"64.44"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-gardens-point","task":"Visual Place Recognition","dataset":"Gardens Point","model":"MixVPR","rank_in_archive_order":2,"of":7,"metrics":{"Recall@1":"91.50"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-hawkins","task":"Visual Place Recognition","dataset":"Hawkins","model":"MixVPR","rank_in_archive_order":7,"of":7,"metrics":{"Recall@1":"25.42"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-laurel-caverns","task":"Visual Place Recognition","dataset":"Laurel Caverns","model":"MixVPR","rank_in_archive_order":6,"of":7,"metrics":{"Recall@1":"29.46"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-test","task":"Visual Place Recognition","dataset":"Mapillary test","model":"MixVPR","rank_in_archive_order":10,"of":12,"metrics":{"Recall@1":"64.0","Recall@10":"80.6","Recall@5":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset":"Mapillary val","model":"MixVPR","rank_in_archive_order":11,"of":18,"metrics":{"Recall@1":"88.2","Recall@10":"94.3","Recall@5":"93.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mid-atlantic","task":"Visual Place Recognition","dataset":"Mid-Atlantic Ridge","model":"MixVPR","rank_in_archive_order":4,"of":7,"metrics":{"Recall@1":"25.74"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-nardo-air","task":"Visual Place Recognition","dataset":"Nardo-Air","model":"MixVPR","rank_in_archive_order":5,"of":7,"metrics":{"Recall@1":"32.39"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-nardo-air-r","task":"Visual Place Recognition","dataset":"Nardo-Air R","model":"MixVPR","rank_in_archive_order":5,"of":8,"metrics":{"Recall@1":"76.06"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-nordland","task":"Visual Place Recognition","dataset":"Nordland","model":"MixVPR","rank_in_archive_order":9,"of":13,"metrics":{"Recall@1":"76.0","Recall@5":"89.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-oxford-robotcar-4","task":"Visual Place Recognition","dataset":"Oxford RobotCar Dataset","model":"MixVPR","rank_in_archive_order":3,"of":7,"metrics":{"Recall@1":"90.05"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-250k","task":"Visual Place Recognition","dataset":"Pittsburgh-250k-test","model":"MixVPR","rank_in_archive_order":8,"of":13,"metrics":{"Recall@1":"94.6","Recall@10":"99.0","Recall@5":"98.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-30k","task":"Visual Place Recognition","dataset":"Pittsburgh-30k-test","model":"MixVPR","rank_in_archive_order":13,"of":22,"metrics":{"Recall@1":"91.52","Recall@5":"95.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-sped","task":"Visual Place Recognition","dataset":"SPED","model":"MixVPR","rank_in_archive_order":7,"of":7,"metrics":{"Recall@1":"85.2","Recall@10":"94.6","Recall@5":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-st-lucia","task":"Visual Place Recognition","dataset":"St Lucia","model":"MixVPR","rank_in_archive_order":7,"of":14,"metrics":{"Recall@1":"99.66"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-vp-air","task":"Visual Place Recognition","dataset":"VP-Air","model":"MixVPR","rank_in_archive_order":5,"of":7,"metrics":{"Recall@1":"10.31"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.02190","atlas_url":"https://app.syntology.ai/?focus=2303.02190","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2303.02190"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.02190\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.02190"},"call":"get_concepts_for_paper(arxiv_id=\"2303.02190\")"}],"by_repo":[{"repo":"amaralibey/mixvpr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9f98401f94b38a64146c4b6163f0cc14700c168dd261247630b0aad2b0663abc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}