{"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/generalized-contrastive-optimization-of","title":"Generalized Contrastive Optimization of Siamese Networks for Place Recognition","arxiv_id":"2103.06638","date":"2021-03-11","proceeding":null,"authors":["María Leyva-Vallina","Nicola Strisciuglio","Nicolai Petkov"],"abstract":"Visual place recognition is a challenging task in computer vision and a key component of camera-based localization and navigation systems. Recently, Convolutional Neural Networks (CNNs) achieved high results and good generalization capabilities. They are usually trained using pairs or triplets of images labeled as either similar or dissimilar, in a binary fashion. In practice, the similarity between two images is not binary, but continuous. Furthermore, training these CNNs is computationally complex and involves costly pair and triplet mining strategies. We propose a Generalized Contrastive loss (GCL) function that relies on image similarity as a continuous measure, and use it to train a siamese CNN. Furthermore, we present three techniques for automatic annotation of image pairs with labels indicating their degree of similarity, and deploy them to re-annotate the MSLS, TB-Places, and 7Scenes datasets. We demonstrate that siamese CNNs trained using the GCL function and the improved annotations consistently outperform their binary counterparts. Our models trained on MSLS outperform the state-of-the-art methods, including NetVLAD, NetVLAD-SARE, AP-GeM and Patch-NetVLAD, and generalize well on the Pittsburgh30k, Tokyo 24/7, RobotCar Seasons v2 and Extended CMU Seasons datasets. Furthermore, training a siamese network using the GCL function does not require complex pair mining. We release the source code at https://github.com/marialeyvallina/generalized_contrastive_loss.","url_abs":"https://arxiv.org/abs/2103.06638v4","url_pdf":"https://arxiv.org/pdf/2103.06638v4.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":"generalized-contrastive-optimization-of","repo_url":"https://github.com/marialeyvallina/generalized_contrastive_loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-place-recognition-on-mapillary-test","task":"Visual Place Recognition","dataset":"Mapillary test","model":"ResNeXt-GCL-PCA","rank_in_archive_order":11,"of":12,"metrics":{"Recall@1":"62.3","Recall@10":"81.1","Recall@5":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-test","task":"Visual Place Recognition","dataset":"Mapillary test","model":"RexNeXt-GCL","rank_in_archive_order":12,"of":12,"metrics":{"Recall@1":"56.0","Recall@10":"75.1","Recall@5":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset":"Mapillary val","model":"ResNeXt GCL + PCA","rank_in_archive_order":15,"of":18,"metrics":{"Recall@1":"80.9","Recall@10":"92.6","Recall@5":"90.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset":"Mapillary val","model":"ResNeXt GCL","rank_in_archive_order":17,"of":18,"metrics":{"Recall@1":"75.5","Recall@10":"88.5","Recall@5":"86.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-place-recognition-on-pittsburgh-30k","task":"Visual Place Recognition","dataset":"Pittsburgh-30k-test","model":"GCL [trained only on MSLS]","rank_in_archive_order":19,"of":22,"metrics":{"Recall@1":"81.94","Recall@5":"94.56"},"uses_additional_data":true},{"leaderboard":"/sota/visual-place-recognition-on-tokyo247","task":"Visual Place Recognition","dataset":"Tokyo247","model":"GCL [trained only on MSLS]","rank_in_archive_order":13,"of":14,"metrics":{"Recall@1":"69.84","Recall@10":"80.63","Recall@5":"84.76"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.06638","atlas_url":"https://app.syntology.ai/?focus=2103.06638","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":"2103.06638"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.06638\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.06638"},"call":"get_concepts_for_paper(arxiv_id=\"2103.06638\")"}],"by_repo":[{"repo":"marialeyvallina/generalized_contrastive_loss","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2303.11739"],"harvested_for_calls":[{"arxiv_id":"2303.11739","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.11739"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.11739\")"}]}],"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":"87d147de8c00f3647e4fa715d936960d4574fc4d1bcf20918539d543bfff9bc1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}