Papers › DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features

DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features

6 Aug 2021ICCV 2021 10arXiv:2108.02927archive 2025-07-28

Min Yang, Dongliang He, Miao Fan, Baorong Shi, Xuetong Xue, Fu Li, Errui Ding, Jizhou Huang

Image Retrieval is a fundamental task of obtaining images similar to the query one from a database. A common image retrieval practice is to firstly retrieve candidate images via similarity search using global image features and then re-rank the candidates by leveraging their local features. Previous learning-based studies mainly focus on either global or local image representation learning to tackle the retrieval task. In this paper, we abandon the two-stage paradigm and seek to design an effective single-stage solution by integrating local and global information inside images into compact image representations. Specifically, we propose a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval. It attentively extracts representative local information with multi-atrous convolutions and self-attention at first. Components orthogonal to the global image representation are then extracted from the local information. At last, the orthogonal components are concatenated with the global representation as a complementary, and then aggregation is performed to generate the final representation. The whole framework is end-to-end differentiable and can be trained with image-level labels. Extensive experimental results validate the effectiveness of our solution and show that our model achieves state-of-the-art image retrieval performances on Revisited Oxford and Paris datasets.

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 23 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 2 repositories, 9 ran (9 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.

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

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

feymanpriv/DOLG officialpytorchMITSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report
feymanpriv/DOLG-paddle mentioned in paperpaddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval (arXiv:2308.04008; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Shiro-LK/python-DOLG mentioned on GitHubpytorchMITSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
dongkyuk/DOLG-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
innat/DOLG-TensorFlow mentioned on GitHubtfSyntology: 5 samples, 4 ran (0 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

23 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 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.

17ran
6unverified

Licence: 0 of the 23 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 3 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”. “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.

feymanpriv/DOLG official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
cache_url core/io.py ran fingerprinted MIT (permissive) · f623b3e3625d4e42 · report fixture: signature url_or_file:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-24
complexity_batchnorm2d core/net.py ran MIT (permissive) · 4136b6e9df422178 · report fixture: signature cx:dict/0/?, w_in:int/0/int · returned dict · level recorded 2026-09-24
complexity_conv2d core/net.py ran MIT (permissive) · b299737079f619a1 · report fixture: signature cx:dict/0/?, w_in:int/0/int, w_out:int/0/int, k:int/0/int, stride:int/0/int, padding:int/0/int, groups:int/0/int, bias:bool/0/bool · returned dict · level recorded 2026-09-24
complexity_maxpool2d core/net.py ran MIT (permissive) · ee4b7c6aef3ebb1f · report fixture: signature cx:dict/0/?, k:int/0/int, stride:int/0/int, padding:int/0/int · returned dict · level recorded 2026-09-24
dump_log_data core/logging.py ran MIT (permissive) · 7defe868d1a6d115 · report fixture: signature data:dict/0/?, data_type:str/0/str, prec:int/0/int · returned str · level recorded 2026-09-25
float_to_decimal core/logging.py ran MIT (permissive) · 99b17e191b358f21 · report fixture: signature data:dict/0/?, prec:int/0/int · returned dict · level recorded 2026-09-25
get_logger in 383 papers core/logging.py ran MIT (permissive) · 8e4e129cb77e7f8b · report fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-24
time_string core/meters.py ran fingerprinted MIT (permissive) · 803bcd86e3301891 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-24
download_url in 32 papers core/io.py unverified MIT (permissive) · e10bd0e3f25f2b57 · report
topk_errors core/meters.py unverified MIT (permissive) · 9fd6e917d49f48e4 · report
Shiro-LK/python-DOLG community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
adaptative_avg_pool2d dolg/resnet_tf2.py ran fingerprinted MIT (permissive) · 0ebf59946affa912 · report fixture: signature x:EagerTensor/4/float, output_dim:int/0/int · returned EagerTensor · level recorded 2026-09-24
extract_embedding_pt dolg/utils/extraction.py ran MIT (permissive) · b428876a811ea78e · report fixture: signature filename:str/0/str, root_dir:str/0/str, model:callable/0/? · returned ndarray · level recorded 2026-09-24
extract_embedding_tf dolg/utils/extraction.py ran MIT (permissive) · 447c96f744ac2f44 · report fixture: signature filename:str/0/str, root_dir:str/0/str, model:callable/0/? · returned ndarray · level recorded 2026-09-24
get_trans_fun dolg/resnet_pt.py ran MIT (permissive) · 2c4de05e1dd24c3b · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-24
process_data in 61 papers dolg/utils/extraction.py ran MIT (permissive) · e2bad3f7809fe40b · report fixture: signature filename:str/0/str, root_dir:str/0/str, mode:str/0/str · returned Tensor · level recorded 2026-09-24
assign_globalmodel dolg/utils/convert_pt_to_tf2.py unverified MIT (permissive) · 7b02caef473b8b28 · report
assign_localmodel dolg/utils/convert_pt_to_tf2.py unverified MIT (permissive) · 0ca3d5ab1b980b50 · report
get_trans_fun dolg/resnet_tf2.py unverified MIT (permissive) · 9796c11dad3f8cd9 · report
innat/DOLG-TensorFlow community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
DOLGLocalBranch models/DOLG.py ran MIT (permissive) · 0e1735ffbfaaabee · report fixture: signature inputs:EagerTensor/4/float, training:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
GeneralizedMeanPooling2D models/DOLG.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · eb1f7279fa17703b · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
MultiAtrous models/DOLG.py ran fingerprinted MIT (permissive) · 6b3acd9aecd4def9 · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
OrthogonalFusion models/DOLG.py ran MIT (permissive) · 399f81dfa6feffde · report fixture: signature inputs:list/1/EagerTensor · returned EagerTensor · level recorded 2026-09-24
DOLGNet models/DOLG.py unverified MIT (permissive) · 73d7a43c9d2acecd · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DOLG (graph method: DOLG). 5 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.

  1. DOLGNet entry · level 0 · unverified · 73d7a43c9d2acecd
  2. DOLGLocalBranch model · level 1 · ran · 0e1735ffbfaaabee
  3. GeneralizedMeanPooling2D model · level 1 · ran · eb1f7279fa17703b
  4. OrthogonalFusion model · level 1 · ran · 399f81dfa6feffde
  5. MultiAtrous model · level 1 · ran · 6b3acd9aecd4def9

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="2108.02927") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image RetrievalRepresentation LearningRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: DOLG

DOLG

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