Papers › TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization

TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization

31 Mar 2022CVPR 2022 1arXiv:2204.00097archive 2025-07-28

Sijie Zhu, Mubarak Shah, Chen Chen

The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2204.00097")

Code

Syntology Ran 1 of 3 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract.

By repository: official repository: 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jeff-zilence/transgeo2022 officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

3 samples harvested; 1 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Jeff-Zilence/TransGeo2022. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

gps2distance Jeff-Zilence/TransGeo2022/dataset/VIGOR.py official repository ran · violated contract fingerprinted MIT (permissive) · a36cbdbad9afc4b2 · report
input_transform Jeff-Zilence/TransGeo2022/dataset/CVACT.py official repository unverified MIT (permissive) · 99a7d0e3a70bb251 · report
input_transform_fov Jeff-Zilence/TransGeo2022/dataset/CVACT.py official repository unverified MIT (permissive) · ebe5c8c48462666d · report

Tasks

AllImage-Based Localizationgeo-localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-Based Localization VIGOR Cross Area TransGeo Hit Rate 21.21 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Cross Area TransGeo Recall@1 18.99 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Cross Area TransGeo Recall@1% 88.94 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Cross Area TransGeo Recall@10 46.91 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Cross Area TransGeo Recall@5 38.24 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Same Area TransGeo Hit Rate 73.09 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Same Area TransGeo Recall@1 61.48 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Same Area TransGeo Recall@1% 99.56 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Same Area TransGeo Recall@10 91.88 #4 of 5 Archive leaderboard report
Image-Based Localization VIGOR Same Area TransGeo Recall@5 87.54 #4 of 5 Archive leaderboard report
Image-Based Localization cvact Transgeo Recall@1 84.95 #5 of 8 Archive leaderboard report
Image-Based Localization cvact Transgeo Recall@1 (%) 98.37 #5 of 8 Archive leaderboard report
Image-Based Localization cvact Transgeo Recall@10 95.78 #5 of 8 Archive leaderboard report
Image-Based Localization cvact Transgeo Recall@5 94.14 #5 of 8 Archive leaderboard report
Image-Based Localization cvusa Transgeo Recall@1 94.08 #5 of 8 Archive leaderboard report
Image-Based Localization cvusa Transgeo Recall@10 99.04 #5 of 8 Archive leaderboard report
Image-Based Localization cvusa Transgeo Recall@5 98.36 #5 of 8 Archive leaderboard report
Image-Based Localization cvusa Transgeo Recall@top1% 99.77 #5 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections