Papers › GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide...

GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization

27 Sep 2023NeurIPS 2023 11arXiv:2309.16020archive 2025-07-28

Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. This task has considerable challenges due to immense variation in geographic landscapes. The image-to-image retrieval-based approaches fail to solve this problem on a global scale as it is not feasible to construct a large gallery of images covering the entire world. Instead, existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. However, their performance is limited by the predefined classes and often results in inaccurate localizations when an image's location significantly deviates from its class center. To overcome these limitations, we propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations. GeoCLIP's location encoder models the Earth as a continuous function by employing positional encoding through random Fourier features and constructing a hierarchical representation that captures information at varying resolutions to yield a semantically rich high-dimensional feature suitable to use even beyond geo-localization. To the best of our knowledge, this is the first work employing GPS encoding for geo-localization. We demonstrate the efficacy of our method via extensive experiments and ablations on benchmark datasets. We achieve competitive performance with just 20% of training data, highlighting its effectiveness even in limited-data settings. Furthermore, we qualitatively demonstrate geo-localization using a text query by leveraging CLIP backbone of our image encoder. The project webpage is available at: https://vicentevivan.github.io/GeoCLIP

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VicenteVivan/geo-clip officialmentioned on GitHubpytorchSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
kelsdoerksen/giga-connectivity mentioned on GitHubSyntology: not harvested report
ramanakshay/hierarchical-geoclip pytorchSyntology: 5 samples, 0 ran · 5 unverified 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

13 samples harvested: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran
8unverified

Licence: 0 of the 13 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

VicenteVivan/geo-clip official repository 8 samples, 5 ran (0 instrument-failed) · 3 unverified
ImageEncoder geoclip/model/GeoCLIP.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 0342fbed5f4dd6e2 · report fixture: returned ImageEncoder · level recorded 2026-09-22
LocationEncoderCapsule geoclip/model/GeoCLIP.py ran MIT (permissive) · 10336c7c42408bd3 · report fixture: returned LocationEncoderCapsule · level recorded 2026-09-22
_extract_image_features geoclip/model/GeoCLIP.py ran · honoured contract fingerprinted MIT (permissive) · 193ffaf24c16bd61 · report fixture: signature output:Tensor/2/float · returned Tensor · level recorded 2026-09-22
equal_earth_projection geoclip/model/GeoCLIP.py ran · honoured contract fingerprinted MIT (permissive) · 0420b6ffe30c1b1b · report fixture: signature L:Tensor/2/float · returned Tensor · level recorded 2026-09-22
load_gps_data geoclip/model/GeoCLIP.py ran · honoured contract MIT (permissive) · 59757f850bed5fc9 · report fixture: signature csv_file:str/0/str · returned Tensor · level recorded 2026-09-22
GaussianEncoding geoclip/model/GeoCLIP.py unverified MIT (permissive) · 88bf24771293c9e0 · report
GeoCLIP geoclip/model/GeoCLIP.py unverified MIT (permissive) · 0db29c57e5099ec7 · report
LocationEncoder geoclip/model/GeoCLIP.py unverified MIT (permissive) · ccb9f7466f37469c · report
ramanakshay/hierarchical-geoclip community (archive-listed) 5 samples, 0 ran · 5 unverified
GaussianEncoding geoclip/model/geoclip.py unverified MIT (permissive) · ae05a9ade5fb928f · report
GeoCLIP geoclip/model/geoclip.py unverified MIT (permissive) · 7e8b0eadc545633d · report
ImageEncoder geoclip/model/geoclip.py unverified MIT (permissive) · 8f9ebe49ed62b249 · report
LocationEncoder geoclip/model/geoclip.py unverified MIT (permissive) · 80221b8324d17fd9 · report
LocationEncoderCapsule geoclip/model/geoclip.py unverified MIT (permissive) · 57f6ab5e0536c43d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for GeoCLIP (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GeoCLIP (graph method: GeoCLIP). 8 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GeoCLIP entry · level 0 · unverified · 0db29c57e5099ec7
  2. ImageEncoder model · level 1 · ran · 0342fbed5f4dd6e2
  3. LocationEncoder model · level 0 · unverified · ccb9f7466f37469c
  4. load_gps_data helper · level 1 · ran · honoured contract · 59757f850bed5fc9
  5. _extract_image_features helper · level 1 · ran · honoured contract · 193ffaf24c16bd61
  6. LocationEncoderCapsule helper · level 1 · ran · 10336c7c42408bd3
  7. equal_earth_projection helper · level 1 · ran · honoured contract · 0420b6ffe30c1b1b
  8. GaussianEncoding helper · level 0 · unverified · 88bf24771293c9e0

harvested Assembly for GeoCLIP (graph method: GeoCLIP). 7 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GeoCLIP entry · level 0 · unverified · 7e8b0eadc545633d
  2. ImageEncoder model · level 0 · unverified · 8f9ebe49ed62b249
  3. LocationEncoder model · level 0 · unverified · 80221b8324d17fd9
  4. load_gps_data helper · level 1 · ran · honoured contract · 59757f850bed5fc9
  5. LocationEncoderCapsule helper · level 0 · unverified · 57f6ab5e0536c43d
  6. equal_earth_projection helper · level 1 · ran · honoured contract · 0420b6ffe30c1b1b
  7. GaussianEncoding helper · level 0 · unverified · ae05a9ade5fb928f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2309.16020") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningGPS EmbeddingsImage RetrievalPhoto geolocation estimationVisual Place Recognitiongeo-localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
GPS Embeddings Geo-Tagged NUS-WIDE (GPS + Visual) GeoCLIP mAP 0.362 #1 of 8 Archive leaderboard report
GPS Embeddings Geo-Tagged NUS-WIDE (GPS Only) GeoCLIP mAP 0.249 #1 of 7 Archive leaderboard report
Photo geolocation estimation GWS15k GeoCLIP City level (25 km) 3.1 #3 of 5 Archive leaderboard report
Photo geolocation estimation GWS15k GeoCLIP Continent level (2500 km) 74.1 #3 of 5 Archive leaderboard report
Photo geolocation estimation GWS15k GeoCLIP Country level (750 km) 45.7 #3 of 5 Archive leaderboard report
Photo geolocation estimation GWS15k GeoCLIP Region level (200 km) 16.9 #3 of 5 Archive leaderboard report
Photo geolocation estimation GWS15k GeoCLIP Street level (1 km) 0.6 #3 of 5 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP City level (25 km) 34.5 #3 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP Continent level (2500 km) 83.8 #3 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP Country level (750 km) 69.7 #3 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP Region level (200 km) 50.7 #3 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP Street level (1 km) 14.1 #3 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k GeoCLIP Training Images 4.7M #3 of 14 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP City level (25 km) 22.2 #1 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP Continent level (2500 km) 76.0 #1 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP Country level (750 km) 57.5 #1 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP Region level (200 km) 36.7 #1 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP Street level (1 km) 11.6 #1 of 6 Archive leaderboard report
Photo geolocation estimation YFCC26k GeoCLIP Training Images 4.7M #1 of 6 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.

Methods

CLIPGPS

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