{"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/towards-seamless-adaptation-of-pre-trained","title":"Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition","arxiv_id":"2402.14505","date":"2024-02-22","proceeding":null,"authors":["Feng Lu","Lijun Zhang","Xiangyuan Lan","Shuting Dong","YaoWei Wang","Chun Yuan"],"abstract":"Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to exploit pre-trained foundation models in visual place recognition (VPR). Due to the inherent difference in training objectives and data between the tasks of model pre-training and VPR, how to bridge the gap and fully unleash the capability of pre-trained models for VPR is still a key issue to address. To this end, we propose a novel method to realize seamless adaptation of pre-trained models for VPR. Specifically, to obtain both global and local features that focus on salient landmarks for discriminating places, we design a hybrid adaptation method to achieve both global and local adaptation efficiently, in which only lightweight adapters are tuned without adjusting the pre-trained model. Besides, to guide effective adaptation, we propose a mutual nearest neighbor local feature loss, which ensures proper dense local features are produced for local matching and avoids time-consuming spatial verification in re-ranking. Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time, and uses about only 3% retrieval runtime of the two-stage VPR methods with RANSAC-based spatial verification. It ranks 1st on the MSLS challenge leaderboard (at the time of submission). The code is released at https://github.com/Lu-Feng/SelaVPR.","url_abs":"https://arxiv.org/abs/2402.14505v3","url_pdf":"https://arxiv.org/pdf/2402.14505v3.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":"towards-seamless-adaptation-of-pre-trained","repo_url":"https://github.com/Lu-Feng/SelaVPR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-place-recognition-on-mapillary-test","task":"Visual Place Recognition","dataset":"Mapillary test","model":"SelaVPR","rank_in_archive_order":9,"of":12,"metrics":{"Recall@1":"73.5","Recall@10":"90.6","Recall@5":"87.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset":"Mapillary val","model":"SelaVPR","rank_in_archive_order":10,"of":18,"metrics":{"Recall@1":"90.8","Recall@10":"97.2","Recall@5":"96.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-nordland","task":"Visual Place Recognition","dataset":"Nordland","model":"SelaVPR","rank_in_archive_order":6,"of":13,"metrics":{"Recall@1":"86.6","Recall@5":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-250k","task":"Visual Place Recognition","dataset":"Pittsburgh-250k-test","model":"SelaVPR","rank_in_archive_order":5,"of":13,"metrics":{"Recall@1":"95.7","Recall@10":"98.8","Recall@5":"99.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-30k","task":"Visual Place Recognition","dataset":"Pittsburgh-30k-test","model":"SelaVPR","rank_in_archive_order":10,"of":22,"metrics":{"Recall@1":"92.8","Recall@5":"97.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-st-lucia","task":"Visual Place Recognition","dataset":"St Lucia","model":"SelaVPR","rank_in_archive_order":5,"of":14,"metrics":{"Recall@1":"99.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-tokyo247","task":"Visual Place Recognition","dataset":"Tokyo247","model":"SelaVPR","rank_in_archive_order":8,"of":14,"metrics":{"Recall@1":"94.0","Recall@10":"96.8","Recall@5":"97.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.14505","atlas_url":"https://app.syntology.ai/?focus=2402.14505","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":"2402.14505"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.14505\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.14505"},"call":"get_concepts_for_paper(arxiv_id=\"2402.14505\")"}],"by_repo":[{"repo":"Lu-Feng/SelaVPR","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.16601"],"harvested_for_calls":[{"arxiv_id":"2502.16601","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.16601"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.16601\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"dd5ceb06baad4ddfddf622681f8b170c181973bedeb77fdbd3aac279d6f2c341","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}