{"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/where-in-the-world-is-this-image-transformer","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","arxiv_id":"2204.13861","date":"2022-04-29","proceeding":null,"authors":["Shraman Pramanick","Ewa M. Nowara","Joshua Gleason","Carlos D. Castillo","Rama Chellappa"],"abstract":"Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem. The challenges include huge diversity of images due to different environmental scenarios, drastic variation in the appearance of the same location depending on the time of the day, weather, season, and more importantly, the prediction is made from a single image possibly having only a few geo-locating cues. For these reasons, most existing works are restricted to specific cities, imagery, or worldwide landmarks. In this work, we focus on developing an efficient solution to planet-scale single-image geo-localization. To this end, we propose TransLocator, a unified dual-branch transformer network that attends to tiny details over the entire image and produces robust feature representation under extreme appearance variations. TransLocator takes an RGB image and its semantic segmentation map as inputs, interacts between its two parallel branches after each transformer layer, and simultaneously performs geo-localization and scene recognition in a multi-task fashion. We evaluate TransLocator on four benchmark datasets - Im2GPS, Im2GPS3k, YFCC4k, YFCC26k and obtain 5.5%, 14.1%, 4.9%, 9.9% continent-level accuracy improvement over the state-of-the-art. TransLocator is also validated on real-world test images and found to be more effective than previous methods.","url_abs":"https://arxiv.org/abs/2204.13861v2","url_pdf":"https://arxiv.org/pdf/2204.13861v2.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":"where-in-the-world-is-this-image-transformer","repo_url":"https://github.com/shramanpramanick/transformer_based_geo-localization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"photo-geolocation-estimation","task_name":"Photo geolocation estimation"},{"task_slug":"scene-recognition","task_name":"Scene Recognition"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"geo-localization","task_name":"geo-localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/photo-geolocation-estimation-on-gws15k","task":"Photo geolocation estimation","dataset":"GWS15k","model":"Translocator","rank_in_archive_order":4,"of":5,"metrics":{"City level (25 km)":"1.1","Continent level (2500 km)":"48.3","Country level (750 km)":"25.5","Region level (200 km)":"8.0","Street level (1 km)":"0.5"},"uses_additional_data":false},{"leaderboard":"/sota/photo-geolocation-estimation-on-im2gps3k","task":"Photo geolocation estimation","dataset":"Im2GPS3k","model":"Translocator","rank_in_archive_order":5,"of":14,"metrics":{"City level (25 km)":"31.1","Continent level (2500 km)":"80.1","Country level (750 km)":"58.9","Region level (200 km)":"46.7","Street level (1 km)":"11.8","Training Images":"4.7M"},"uses_additional_data":false},{"leaderboard":"/sota/photo-geolocation-estimation-on-yfcc26k","task":"Photo geolocation estimation","dataset":"YFCC26k","model":"Translocator","rank_in_archive_order":4,"of":6,"metrics":{"City level (25 km)":"17.8","Continent level (2500 km)":"60.6","Country level (750 km)":"41.3","Region level (200 km)":"28.0","Street level (1 km)":"7.2","Training Images":"4.7M"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.13861","atlas_url":"https://app.syntology.ai/?focus=2204.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13861"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/shramanpramanick/transformer_based_geo-localization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"374dfca88d741d74","entry":"topk_accuracy","repo":"shramanpramanick/transformer_based_geo-localization","repo_kind":"official","path":"experiment_codes/ViT_RGB_train.py","file_url":"https://github.com/shramanpramanick/transformer_based_geo-localization/blob/HEAD/experiment_codes/ViT_RGB_train.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"374dfca88d741d74"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}