Papers › Large-Scale Image Retrieval with Attentive Deep Local Features

Large-Scale Image Retrieval with Attentive Deep Local Features

19 Dec 2016ICCV 2017 10arXiv:1612.06321archive 2025-07-28

Hyeonwoo Noh, Andre Araujo, Jack Sim, Tobias Weyand, Bohyung Han

We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature). The new feature is based on convolutional neural networks, which are trained only with image-level annotations on a landmark image dataset. To identify semantically useful local features for image retrieval, we also propose an attention mechanism for keypoint selection, which shares most network layers with the descriptor. This framework can be used for image retrieval as a drop-in replacement for other keypoint detectors and descriptors, enabling more accurate feature matching and geometric verification. Our system produces reliable confidence scores to reject false positives---in particular, it is robust against queries that have no correct match in the database. To evaluate the proposed descriptor, we introduce a new large-scale dataset, referred to as Google-Landmarks dataset, which involves challenges in both database and query such as background clutter, partial occlusion, multiple landmarks, objects in variable scales, etc. We show that DELF outperforms the state-of-the-art global and local descriptors in the large-scale setting by significant margins. Code and dataset can be found at the project webpage: https://github.com/tensorflow/models/tree/master/research/delf .

PaperPDFConference PDFCodeCode Syntology ran

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

No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 12 samples below come from 1 community repository. Syntology harvested code from tensorflow/models for 4 other papers.

tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 12 samples that ran have no recorded date.

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

tensorflow/models officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Ash-Lee233/delf mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
insikk/delf_enhanced mentioned on GitHubtfSyntology: not harvested report
jandaldrop/landmark-recognition-challenge mentioned on GitHubtfSyntology: not harvested report
nashory/DeLF-pytorch mentioned on GitHubpytorchMITSyntology: 12 samples, 12 ran (2 instrument-failed) · 0 unverified report
pandigreat/DELF mentioned on GitHubpytorchSyntology: not harvested report
qianlinjun/delf-pytorch mentioned on GitHubpytorchSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MindSpore-paper-code-3/code2 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code8 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-5 mindsporeSyntology: not harvested report
kingcong/delf mindsporenot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

12 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
9ran

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nashory/DeLF-pytorch. “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”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

nashory/DeLF-pytorch community (archive-listed) 12 samples, 12 ran (2 instrument-failed) · 0 unverified
CalculateKeypointCenters helper/delf_helper.py ran fingerprinted MIT (permissive) · 5981d120f5eb39af · report fixture: signature rf_boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
CalculateReceptiveBoxes helper/delf_helper.py ran MIT (permissive) · 849ed1ad570b067c · report fixture: signature height:int/0/int, width:int/0/int, rf:int/0/int, stride:int/0/int, padding:int/0/int · returned Tensor · level recorded 2026-09-26
GenerateCoordinates helper/delf_helper.py ran fingerprinted MIT (permissive) · 5a69d65b6d87d22f · report fixture: signature h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-26
find_classes in 61 papers extract/folder.py ran · our draft was wrong MIT (permissive) · 52d10a10fb72fb9f · report fixture: signature dir:str/0/str · returned tuple · level recorded 2026-09-24
get_inliers helper/matcher.py ran fingerprinted MIT (permissive) · 74aabe4219cf5fe5 · report fixture: signature locations_1:ndarray/2/float, descriptors_1:ndarray/2/float, locations_2:ndarray/2/float, descriptors_2:ndarray/2/float · returned tuple · level recorded 2026-09-26
get_loader in 62 papers train/dataloader.py ran MIT (permissive) · 7a9dec8d9dfd2eb7 · report fixture: signature train_path:str/0/str, val_path:str/0/str, stage:str/0/str, train_batch_size:int/0/int, val_batch_size:int/0/int, sample_size:int/0/int, crop_size:int/0/int, workers:int/0/int · returned tuple · level recorded 2026-09-26
has_file_allowed_extension in 38 papers extract/folder.py ran MIT (permissive) · e800290c5ea55efd · report fixture: signature filename:str/0/str, extensions:list/1/str · returned bool · level recorded 2026-09-26
load_image_into_numpy_array in 5 papers helper/matcher.py ran MIT (permissive) · 740767f98e8c32bb · report fixture: signature image:Image/0/? · returned ndarray · level recorded 2026-09-26
make_dataset in 144 papers extract/folder.py ran MIT (permissive) · 100e7ed2b7d0980f · report fixture: signature dir:str/0/str, class_to_idx:dict/0/?, extensions:tuple/1/str · returned list · level recorded 2026-09-26
plot_overlap in 37 papers utils/logger.py ran · our draft was wrong MIT (permissive) · 50afa2863ffd9fde · report fixture: signature logger:MockLogger/0/?, names:NoneType/0/? · returned list · level recorded, date not recorded
read_image in 73 papers helper/matcher.py ran MIT (permissive) · 69b8e79cea9fed25 · report fixture: signature image_path:str/0/str · returned ndarray · level recorded 2026-09-26
str2bool in 533 papers train/config.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 248284f69adfeaad · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded

Tasks

Image RetrievalRetrieval

Datasets

Introduced by this paper, per the archive.

Google Landmarks

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval Oxf105k DELF+FT+ATT+DIR+QE MAP 88.5% #2 of 9 Archive leaderboard report
Image Retrieval Oxf105k DELF+FT+ATT MAP 82.6% #5 of 9 Archive leaderboard report
Image Retrieval Oxf5k DELF+FT+ATT+DIR+QE MAP 90.0% #3 of 11 Archive leaderboard report
Image Retrieval Oxf5k DELF+FT+ATT MAP 83.8% #5 of 11 Archive leaderboard report
Image Retrieval Par106k DELF+FT+ATT+DIR+QE mAP 92.8% #2 of 7 Archive leaderboard report
Image Retrieval Par106k DELF+FT+ATT mAP 81.7% #4 of 7 Archive leaderboard report
Image Retrieval Par6k DELF+FT+ATT+DIR+QE mAP 95.7% #2 of 7 Archive leaderboard report
Image Retrieval Par6k DELF+FT+ATT mAP 85.0% #6 of 7 Archive leaderboard report
Image Retrieval ROxford (Hard) DELF–HQE+SP mAP 50.3 #9 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) DELF–ASMK*+SP mAP 43.1 #11 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) DELF–HQE+SP mAP 73.4 #8 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) DELF–ASMK*+SP mAP 67.8 #10 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) DELF–HQE+SP mAP 69.3 #8 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) DELF–ASMK*+SP mAP 55.4 #12 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) DELF–HQE+SP mAP 84.0 #7 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) DELF–ASMK*+SP mAP 76.9 #11 of 23 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