Papers › Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

2 Mar 2021CVPR 2021 1arXiv:2103.01486archive 2025-07-28

Stephen Hausler, Sourav Garg, Ming Xu, Michael Milford, Tobias Fischer

Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world. This paper introduces Patch-NetVLAD, which provides a novel formulation for combining the advantages of both local and global descriptor methods by deriving patch-level features from NetVLAD residuals. Unlike the fixed spatial neighborhood regime of existing local keypoint features, our method enables aggregation and matching of deep-learned local features defined over the feature-space grid. We further introduce a multi-scale fusion of patch features that have complementary scales (i.e. patch sizes) via an integral feature space and show that the fused features are highly invariant to both condition (season, structure, and illumination) and viewpoint (translation and rotation) changes. Patch-NetVLAD outperforms both global and local feature descriptor-based methods with comparable compute, achieving state-of-the-art visual place recognition results on a range of challenging real-world datasets, including winning the Facebook Mapillary Visual Place Recognition Challenge at ECCV2020. It is also adaptable to user requirements, with a speed-optimised version operating over an order of magnitude faster than the state-of-the-art. By combining superior performance with improved computational efficiency in a configurable framework, Patch-NetVLAD is well suited to enhance both stand-alone place recognition capabilities and the overall performance of SLAM systems.

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 5 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

QVPR/Patch-NetVLAD officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
gmberton/VPR-datasets-downloader mentioned on GitHubSyntology: not harvested report
marialeyvallina/generalized_contrastive_loss mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Data-efficient Large Scale Place Recognition with Graded Similarity Supervision (arXiv:2303.11739; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
taowenyin/PatchNetVLAD mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 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.

1ran · our draft was wrong
2ran; the contract check could not run
1ran
1unverified

Licence: 0 of the 5 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.

QVPR/Patch-NetVLAD official repository 3 samples, 3 ran (2 instrument-failed) · 0 unverified
PatchNetVLAD patchnetvlad/models/patchnetvlad.py ran MIT (permissive) · 3df22a709177cb8f · report fixture: returned PatchNetVLAD · level recorded 2026-09-22
get_integral_feature patchnetvlad/models/patchnetvlad.py ran · our draft was wrong fingerprinted MIT (permissive) · 9402f303f3ae9ff0 · report fixture: signature feat_in:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_square_regions_from_integral patchnetvlad/models/patchnetvlad.py ran; the contract check could not run (RAISES) MIT (permissive) · d8abdf376063a44c · report fixture: signature feat_integral:Tensor/4/float, patch_size:int/0/int, patch_stride:int/0/int · returned Tensor · level recorded 2026-09-22
taowenyin/PatchNetVLAD community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_square_regions_from_integral patchnetvlad/models/patchnetvlad.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d062e48ac9b786f0 · report fixture: signature feat_integral:Tensor/4/float, patch_size:int/0/int, patch_stride:int/0/int · returned Tensor · level recorded 2026-09-22
PatchNetVLAD patchnetvlad/models/patchnetvlad.py unverified MIT (permissive) · 044ac142e4307cc8 · 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 Patch-NetVLAD (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Patch-NetVLAD (graph method: Patch-NetVLAD). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PatchNetVLAD entry · level 1 · ran · 3df22a709177cb8f
  2. get_integral_feature helper · level 1 · ran · our draft was wrong · 9402f303f3ae9ff0
  3. get_square_regions_from_integral helper · level 1 · ran; the contract check could not run (RAISES) · d8abdf376063a44c

harvested Assembly for Patch-NetVLAD (graph method: Patch-NetVLAD). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PatchNetVLAD entry · level 0 · unverified · 044ac142e4307cc8
  2. get_integral_feature helper · level 1 · ran · our draft was wrong · 9402f303f3ae9ff0
  3. get_square_regions_from_integral helper · level 1 · ran; the contract check could not run (RAISES) · d062e48ac9b786f0

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="2103.01486") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyVisual LocalizationVisual Place Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Localization Extended CMU Seasons Patch-NetVLAD Acc @ .25m, 2° 0.118 #1 of 1 Archive leaderboard report
Visual Localization Extended CMU Seasons Patch-NetVLAD Acc @ .5m, 5° 0.362 #1 of 1 Archive leaderboard report
Visual Localization Extended CMU Seasons Patch-NetVLAD Acc @ 5m, 10° 0.962 #1 of 1 Archive leaderboard report
Visual Localization RobotCar Seasons v2 Patch-NetVLAD Acc @ .25m, 2° 0.096 #1 of 1 Archive leaderboard report
Visual Localization RobotCar Seasons v2 Patch-NetVLAD Acc @ .5m, 5° 0.353 #1 of 1 Archive leaderboard report
Visual Localization RobotCar Seasons v2 Patch-NetVLAD Acc @ 5m, 10° 0.909 #1 of 1 Archive leaderboard report
Visual Place Recognition Mapillary val Patch-NetVLAD Recall@1 79.5 #16 of 18 Archive leaderboard report
Visual Place Recognition Mapillary val Patch-NetVLAD Recall@10 87.7 #16 of 18 Archive leaderboard report
Visual Place Recognition Mapillary val Patch-NetVLAD Recall@5 86.2 #16 of 18 Archive leaderboard report
Visual Place Recognition Nordland Patch-NetVLAD Recall@1 58.4 #10 of 13 Archive leaderboard report
Visual Place Recognition Nordland Patch-NetVLAD Recall@5 74.6 #10 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test Patch-NetVLAD Recall@1 88.7 #16 of 22 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test Patch-NetVLAD Recall@5 94.5 #16 of 22 Archive leaderboard report
Visual Place Recognition Tokyo247 Patch-NetVLAD Recall@1 86 #11 of 14 Archive leaderboard report
Visual Place Recognition Tokyo247 Patch-NetVLAD Recall@10 90.5 #11 of 14 Archive leaderboard report
Visual Place Recognition Tokyo247 Patch-NetVLAD Recall@5 88.6 #11 of 14 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