{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/optimal-transport-aggregation-for-visual","title":"Optimal Transport Aggregation for Visual Place Recognition","arxiv_id":"2311.15937","date":"2023-11-27","proceeding":"CVPR 2024 1","authors":["Sergio Izquierdo","Javier Civera"],"abstract":"The task of Visual Place Recognition (VPR) aims to match a query image against references from an extensive database of images from different places, relying solely on visual cues. State-of-the-art pipelines focus on the aggregation of features extracted from a deep backbone, in order to form a global descriptor for each image. In this context, we introduce SALAD (Sinkhorn Algorithm for Locally Aggregated Descriptors), which reformulates NetVLAD's soft-assignment of local features to clusters as an optimal transport problem. In SALAD, we consider both feature-to-cluster and cluster-to-feature relations and we also introduce a 'dustbin' cluster, designed to selectively discard features deemed non-informative, enhancing the overall descriptor quality. Additionally, we leverage and fine-tune DINOv2 as a backbone, which provides enhanced description power for the local features, and dramatically reduces the required training time. As a result, our single-stage method not only surpasses single-stage baselines in public VPR datasets, but also surpasses two-stage methods that add a re-ranking with significantly higher cost. Code and models are available at https://github.com/serizba/salad.","url_abs":"https://arxiv.org/abs/2311.15937v2","url_pdf":"https://arxiv.org/pdf/2311.15937v2.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":"optimal-transport-aggregation-for-visual","repo_url":"https://github.com/serizba/salad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"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":"DINOv2 SALAD","rank_in_archive_order":8,"of":12,"metrics":{"Recall@1":"75","Recall@10":"91.3","Recall@5":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset":"Mapillary val","model":"DINOv2 SALAD","rank_in_archive_order":8,"of":18,"metrics":{"Recall@1":"92.2","Recall@10":"97","Recall@5":"96.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-nordland","task":"Visual Place Recognition","dataset":"Nordland","model":"DINOv2 SALAD (1-frame thr.)","rank_in_archive_order":7,"of":13,"metrics":{"Recall@1":"85.2","Recall@5":"98.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-250k","task":"Visual Place Recognition","dataset":"Pittsburgh-250k-test","model":"DINOv2 SALAD","rank_in_archive_order":6,"of":13,"metrics":{"Recall@1":"95.1","Recall@10":"99.1","Recall@5":"98.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-sped","task":"Visual Place Recognition","dataset":"SPED","model":"DINOv2 SALAD","rank_in_archive_order":3,"of":7,"metrics":{"Recall@1":"92.1","Recall@10":"96.5","Recall@5":"96.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.15937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15937"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/serizba/salad","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"0bfa87e7ee328290","entry":"input_transform","repo":"serizba/salad","repo_kind":"official","path":"dataloaders/PittsburgDataset.py","file_url":"https://github.com/serizba/salad/blob/HEAD/dataloaders/PittsburgDataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0bfa87e7ee328290"}},{"code_sha256_prefix":"cc0d6b2496e86c33","entry":"log_otp_solver","repo":"serizba/salad","repo_kind":"official","path":"models/aggregators/salad.py","file_url":"https://github.com/serizba/salad/blob/HEAD/models/aggregators/salad.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cc0d6b2496e86c33"}},{"code_sha256_prefix":"822eb8660b831cf3","entry":"get_250k_val_set","repo":"serizba/salad","repo_kind":"official","path":"dataloaders/PittsburgDataset.py","file_url":"https://github.com/serizba/salad/blob/HEAD/dataloaders/PittsburgDataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"822eb8660b831cf3"}},{"code_sha256_prefix":"68f14b22cb2b7f18","entry":"get_loss","repo":"serizba/salad","repo_kind":"official","path":"utils/losses.py","file_url":"https://github.com/serizba/salad/blob/HEAD/utils/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"68f14b22cb2b7f18"}},{"code_sha256_prefix":"6d34ff3423316bc7","entry":"get_matching_probs","repo":"serizba/salad","repo_kind":"official","path":"models/aggregators/salad.py","file_url":"https://github.com/serizba/salad/blob/HEAD/models/aggregators/salad.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6d34ff3423316bc7"}},{"code_sha256_prefix":"831dbf17d208a75e","entry":"get_miner","repo":"serizba/salad","repo_kind":"official","path":"utils/losses.py","file_url":"https://github.com/serizba/salad/blob/HEAD/utils/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"831dbf17d208a75e"}},{"code_sha256_prefix":"c9c5d63f9d8b8966","entry":"get_whole_val_set","repo":"serizba/salad","repo_kind":"official","path":"dataloaders/PittsburgDataset.py","file_url":"https://github.com/serizba/salad/blob/HEAD/dataloaders/PittsburgDataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c9c5d63f9d8b8966"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}