Papers › Global Features are All You Need for Image Retrieval and Reranking

Global Features are All You Need for Image Retrieval and Reranking

14 Aug 2023ICCV 2023 1arXiv:2308.06954archive 2025-07-28

Shihao Shao, KaiFeng Chen, Arjun Karpur, Qinghua Cui, Andre Araujo, Bingyi Cao

Image retrieval systems conventionally use a two-stage paradigm, leveraging global features for initial retrieval and local features for reranking. However, the scalability of this method is often limited due to the significant storage and computation cost incurred by local feature matching in the reranking stage. In this paper, we present SuperGlobal, a novel approach that exclusively employs global features for both stages, improving efficiency without sacrificing accuracy. SuperGlobal introduces key enhancements to the retrieval system, specifically focusing on the global feature extraction and reranking processes. For extraction, we identify sub-optimal performance when the widely-used ArcFace loss and Generalized Mean (GeM) pooling methods are combined and propose several new modules to improve GeM pooling. In the reranking stage, we introduce a novel method to update the global features of the query and top-ranked images by only considering feature refinement with a small set of images, thus being very compute and memory efficient. Our experiments demonstrate substantial improvements compared to the state of the art in standard benchmarks. Notably, on the Revisited Oxford+1M Hard dataset, our single-stage results improve by 7.1%, while our two-stage gain reaches 3.7% with a strong 64,865x speedup. Our two-stage system surpasses the current single-stage state-of-the-art by 16.3%, offering a scalable, accurate alternative for high-performing image retrieval systems with minimal time overhead. Code: https://github.com/ShihaoShao-GH/SuperGlobal.

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 18 code samples harvested from 1 repository linked to this paper: 14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 14 ran (12 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shihaoshao-gh/superglobal officialmentioned in papermentioned on GitHubpytorchSyntology: 18 samples, 14 ran (2 instrument-failed) · 4 unverified report
edwardguil/CVNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Correlation Verification for Image Retrieval (arXiv:2204.01458; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result); 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

18 samples harvested: 14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 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.

2ran · our draft was wrong
12ran
4unverified

Licence: 0 of the 18 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 shihaoshao-gh/superglobal. “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 6 samples 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.

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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

shihaoshao-gh/superglobal official repository 18 samples, 14 ran (2 instrument-failed) · 4 unverified
BasicTransform model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · 5fbea145e2e1ef9a · report fixture: returned BasicTransform · level recorded 2026-09-22
BottleneckTransform model/CVNet_Rerank_model.py ran MIT (permissive) · bc2d89d946121f78 · report fixture: returned BottleneckTransform · level recorded 2026-09-22
GeneralizedMeanPooling model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · 9119b8d4c98f5ced · report fixture: returned GeneralizedMeanPooling · level recorded 2026-09-22
GeneralizedMeanPoolingP model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · ae68dadce75b3fe4 · report fixture: returned GeneralizedMeanPoolingP · level recorded 2026-09-22
GlobalHead model/CVNet_Rerank_model.py ran MIT (permissive) · 1a832022e62d5c07 · report fixture: returned GlobalHead · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
model/CVNet_Rerank_model.py ran MIT (permissive) · 8aba530c55c5eb3a · report fixture: returned ResBlock · level recorded 2026-09-22
ResStage model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · c2d48a0c32a3d652 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ResStemIN model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · b7468ec69b24b267 · report fixture: returned ResStemIN · level recorded 2026-09-22
extract_feat_res_pycls model/CVNet_Rerank_model.py ran · our draft was wrong MIT (permissive) · 03fb3b12debca8c5 · report fixture: signature img:Tensor/4/float, backbone:callable/0/?, feat_ids:list/1/int, bottleneck_ids:list/1/int, lids:list/1/int · returned list · level recorded 2026-09-22
gemp model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · af08767ec93f2b28 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
get_trans_fun model/CVNet_Rerank_model.py ran · our draft was wrong MIT (permissive) · 00a9dda76ea3fd57 · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-22
relup model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · 2031bc64eb8b91b6 · report fixture: returned relup · level recorded 2026-09-22
rgem model/CVNet_Rerank_model.py ran fingerprinted MIT (permissive) · cd3b5d6af1e69d75 · report fixture: returned rgem · level recorded 2026-09-22
sgem model/CVNet_Rerank_model.py ran MIT (permissive) · 292667a5366078d8 · report fixture: signature x:list/1/Tensor · returned Tensor · level recorded 2026-09-24
CVLearner model/CVNet_Rerank_model.py unverified MIT (permissive) · 8bd337cafee60b1d · report
CVNet_Rerank model/CVNet_Rerank_model.py unverified MIT (permissive) · 920c4a63177050ae · report
Correlation in 6 papers model/CVNet_Rerank_model.py unverified MIT (permissive) · 6348d625e9ec5a11 · report
ResNet in 139 papers model/CVNet_Rerank_model.py unverified MIT (permissive) · 8561c39b1b352e43 · 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 SuperGlobal (graph method: SuperGlobal). 18 bricks; individually on a fixture: 14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. CVNet_Rerank entry · level 0 · unverified · 920c4a63177050ae
  2. CVLearner helper · level 0 · unverified · 8bd337cafee60b1d
  3. Correlation helper · level 0 · unverified · 6348d625e9ec5a11
  4. ResNet model · level 0 · unverified · 8561c39b1b352e43
  5. extract_feat_res_pycls helper · level 1 · ran · our draft was wrong · 03fb3b12debca8c5
  6. gemp helper · level 1 · ran · af08767ec93f2b28
  7. relup helper · level 1 · ran · 2031bc64eb8b91b6
  8. rgem helper · level 1 · ran · cd3b5d6af1e69d75
  9. sgem helper · level 1 · ran · 292667a5366078d8
  10. GlobalHead helper · level 1 · ran · 1a832022e62d5c07
  11. ResStage helper · level 1 · ran · c2d48a0c32a3d652
  12. ResStemIN helper · level 1 · ran · b7468ec69b24b267
  13. GeneralizedMeanPoolingP helper · level 1 · ran · ae68dadce75b3fe4
  14. ResBlock helper · level 1 · ran · 8aba530c55c5eb3a
  15. get_trans_fun helper · level 1 · ran · our draft was wrong · 00a9dda76ea3fd57
  16. GeneralizedMeanPooling helper · level 1 · ran · 9119b8d4c98f5ced
  17. BasicTransform helper · level 1 · ran · 5fbea145e2e1ef9a
  18. BottleneckTransform helper · level 1 · ran · bc2d89d946121f78

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="2308.06954") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AllImage RetrievalRerankingRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval ROxford (Hard) SuperGlobal mAP 80.2 #1 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) SuperGlobal mAP 86.7 #2 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.

Methods

ArcFace

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