Papers › NetVLAD: CNN architecture for weakly supervised place recognition

NetVLAD: CNN architecture for weakly supervised place recognition

23 Nov 2015CVPR 2016 6arXiv:1511.07247archive 2025-07-28

Relja Arandjelović, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state-of-the-art compact image representations on standard image retrieval benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1511.07247")

Code

Syntology Ran 0 of 12 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run.

By repository: community (archive-listed): 12 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

14 repositories listed; official and paper-mentioned ones first.

Relja/netvlad officialMIT report
ChienYiChi/kaggle-panda-challenge mentioned on GitHubpytorchMIT report
MubarizZaffar/VPR-Bench mentioned on GitHubMIT report
Nanne/pytorch-NetVlad mentioned on GitHubpytorch report
YanLiqi/HAF mentioned on GitHubpytorchMIT report
gmberton/geo_warp mentioned on GitHubpytorch report
goodproj13/DenserNet mentioned on GitHubpytorchMIT report
keetsky/Net_ghostVLAD-pytorch mentioned on GitHubpytorchMIT report
lyakaap/NetVLAD-pytorch mentioned on GitHubpytorchMIT report
vinnik-dmitry07/PlaceRecognition mentioned on GitHubpytorch report
yxgeee/SFRS mentioned on GitHubpytorchMIT report
yxgeee/openibl mentioned on GitHubpytorchMIT 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

12unverified

Licence: 0 of the 12 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; each sample names its own and says which. “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.

accuracy ChienYiChi/kaggle-panda-challenge/src/utils.py community (archive-listed) unverified MIT (permissive) · e193c34cf5c21621 · report
blue_ratio_selection ChienYiChi/kaggle-panda-challenge/src/dataset.py community (archive-listed) unverified MIT (permissive) · dc26c333e39e8ca9 · report
compute_weights ChienYiChi/kaggle-panda-challenge/src/generate_weights.py community (archive-listed) unverified MIT (permissive) · d40e6d73305e43d0 · report
crop_white ChienYiChi/kaggle-panda-challenge/src/preprocess.py community (archive-listed) unverified MIT (permissive) · d9a827e75b532949 · report
evaluate uzh-rpg/netvlad_tf_open/python/netvlad_tf/precision_recall.py community (archive-listed) unverified MIT (permissive) · 3e2532b6c170f972 · report
get_tiles ChienYiChi/kaggle-panda-challenge/src/dataset.py community (archive-listed) unverified MIT (permissive) · aa3e63d35834e2eb · report
get_tiles_brs ChienYiChi/kaggle-panda-challenge/src/dataset.py community (archive-listed) unverified MIT (permissive) · 4f6eccb6a67664d3 · report
matconvnetNormalize uzh-rpg/netvlad_tf_open/python/netvlad_tf/layers.py community (archive-listed) unverified MIT (permissive) · 0fe927e3be8d314c · report
name_to_tile ChienYiChi/kaggle-panda-challenge/src/generate_weights.py community (archive-listed) unverified MIT (permissive) · 135081edae587c1d · report
netVLAD uzh-rpg/netvlad_tf_open/python/netvlad_tf/layers.py community (archive-listed) unverified MIT (permissive) · 1bfe629b56c533b1 · report
quadratic_weighted_kappa ChienYiChi/kaggle-panda-challenge/src/engine.py community (archive-listed) unverified MIT (permissive) · 374f0d897ab43c7e · report
setup_logger ChienYiChi/kaggle-panda-challenge/src/utils.py community (archive-listed) unverified MIT (permissive) · f7ee730a2131702b · report

Tasks

Image RetrievalRetrievalVisual Place Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Place Recognition 17 Places NetVLAD Recall@1 61.58 #6 of 8 Archive leaderboard report
Visual Place Recognition Baidu Mall NetVLAD Recall@1 53.10 #5 of 8 Archive leaderboard report
Visual Place Recognition Berlin Kudamm NetVLAD Recall@1 38.21 #4 of 4 Archive leaderboard report
Visual Place Recognition Gardens Point NetVLAD Recall@1 58.50 #6 of 7 Archive leaderboard report
Visual Place Recognition Hawkins NetVLAD Recall@1 34.75 #3 of 7 Archive leaderboard report
Visual Place Recognition Laurel Caverns NetVLAD Recall@1 39.29 #4 of 7 Archive leaderboard report
Visual Place Recognition Mid-Atlantic Ridge NetVLAD Recall@1 25.74 #3 of 7 Archive leaderboard report
Visual Place Recognition Nardo-Air NetVLAD Recall@1 19.72 #6 of 7 Archive leaderboard report
Visual Place Recognition Nardo-Air R NetVLAD Recall@1 60.56 #8 of 8 Archive leaderboard report
Visual Place Recognition Oxford RobotCar Dataset NetVLAD Recall@1 52.88 #4 of 7 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test NetVLAD Recall@1 86.08 #18 of 22 Archive leaderboard report
Visual Place Recognition St Lucia NetVLAD Recall@1 57.92 #12 of 14 Archive leaderboard report
Visual Place Recognition VP-Air NetVLAD Recall@1 6.39 #7 of 7 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