Papers › G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large...

G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models

23 May 2024arXiv:2405.14702archive 2025-07-28

Pengyue Jia, Yiding Liu, Xiaopeng Li, Yuhao Wang, Yantong Du, Xiao Han, Xuetao Wei, Shuaiqiang Wang, Dawei Yin, Xiangyu Zhao

Worldwide geolocalization aims to locate the precise location at the coordinate level of photos taken anywhere on the Earth. It is very challenging due to 1) the difficulty of capturing subtle location-aware visual semantics, and 2) the heterogeneous geographical distribution of image data. As a result, existing studies have clear limitations when scaled to a worldwide context. They may easily confuse distant images with similar visual contents, or cannot adapt to various locations worldwide with different amounts of relevant data. To resolve these limitations, we propose G3, a novel framework based on Retrieval-Augmented Generation (RAG). In particular, G3 consists of three steps, i.e., Geo-alignment, Geo-diversification, and Geo-verification to optimize both retrieval and generation phases of worldwide geolocalization. During Geo-alignment, our solution jointly learns expressive multi-modal representations for images, GPS and textual descriptions, which allows us to capture location-aware semantics for retrieving nearby images for a given query. During Geo-diversification, we leverage a prompt ensembling method that is robust to inconsistent retrieval performance for different image queries. Finally, we combine both retrieved and generated GPS candidates in Geo-verification for location prediction. Experiments on two well-established datasets IM2GPS3k and YFCC4k verify the superiority of G3 compared to other state-of-the-art methods. Our code and data are available online for reproduction.

PaperPDFCodeCode 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="2405.14702")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

applied-machine-learning-lab/g3 officialmentioned in paperpytorchApache-2.0 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

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
2ran
5unverified

Licence: 0 of the 8 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 applied-machine-learning-lab/g3. “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.

basic_encoding applied-machine-learning-lab/g3/utils/rff/functional.py official repository ran Apache-2.0 (permissive) · 2d2bc5c34037e15b · report
encode_image applied-machine-learning-lab/g3/llm_predict.py official repository ran · our draft was wrong Apache-2.0 (permissive) · f41cb1a19b154297 · report
gaussian_encoding applied-machine-learning-lab/g3/utils/rff/functional.py official repository ran Apache-2.0 (permissive) · 93245a6fbe3c4415 · report
get_response applied-machine-learning-lab/g3/llm_predict.py official repository unverified Apache-2.0 (permissive) · 14ab877eaf533dfb · report
get_response applied-machine-learning-lab/g3/llm_predict_hf.py official repository unverified Apache-2.0 (permissive) · a32ec97a24a3f7e6 · report
get_response_rag applied-machine-learning-lab/g3/llm_predict.py official repository unverified Apache-2.0 (permissive) · 96b18a8aed30ff38 · report
get_response_rag applied-machine-learning-lab/g3/llm_predict_hf.py official repository unverified Apache-2.0 (permissive) · 09307a86733e770b · report
sample_b applied-machine-learning-lab/g3/utils/rff/functional.py official repository unverified Apache-2.0 (permissive) · 43e5f269780ac7f5 · report

Tasks

Photo geolocation estimationRAGRetrievalRetrieval-augmented Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Photo geolocation estimation Im2GPS3k G3 City level (25 km) 40.94 #2 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k G3 Continent level (2500 km) 84.68 #2 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k G3 Country level (750 km) 71.24 #2 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k G3 Region level (200 km) 55.56 #2 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k G3 Street level (1 km) 16.65 #2 of 14 Archive leaderboard report
Photo geolocation estimation Im2GPS3k G3 Training Images 4.12M #2 of 14 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 City (25 km) 35.89 #3 of 4 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 Continent (2500 km) 78.15 #3 of 4 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 Country (750 km) 64.26 #3 of 4 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 Median Error (km) / #3 of 4 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 Region (200 km) 46.98 #3 of 4 Archive leaderboard report
Photo geolocation estimation YFCC4k G3 Street (1 km) 23.99 #3 of 4 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

GPS

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