Papers › With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual...

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

29 Apr 2021ICCV 2021 10arXiv:2104.14548archive 2025-07-28

Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a contrastive loss, we are interested in using positives from other instances in the dataset. Our method, Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR), samples the nearest neighbors from the dataset in the latent space, and treats them as positives. This provides more semantic variations than pre-defined transformations. We find that using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification, from 71.7% to 75.6%, outperforming previous state-of-the-art methods. On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.8% to 56.5%. On transfer learning benchmarks our method outperforms state-of-the-art methods (including supervised learning with ImageNet) on 8 out of 12 downstream datasets. Furthermore, we demonstrate empirically that our method is less reliant on complex data augmentations. We see a relative reduction of only 2.1% ImageNet Top-1 accuracy when we train using only random crops.

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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 2 repositories, 4 ran (4 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 2 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.

beresandras/contrastive-classification-keras mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
vturrisi/solo-learn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Baselines with Momentum Contrastive Learning (arXiv:2003.04297; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified), Whitening for Self-Supervised Representation Learning (arXiv:2007.06346; that paper's own run record: 11 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified) and ReSSL: Relational Self-Supervised Learning with Weak Augmentation (arXiv:2107.09282; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 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

5 samples harvested: 4 ran (of which 4 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; every one of the 4 samples that ran constructed an object rather than computing a result. “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.

4ran
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 3 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.

beresandras/contrastive-classification-keras community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ContrastiveModel algorithms.py ran MIT (permissive) · acc020a5fafd0a3c · report fixture: returned ContrastiveModel · level recorded 2026-09-22
NNCLR algorithms.py unverified MIT (permissive) · a8d39573526af033 · report
lightly-ai/lightly community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
NNCLR lightly/models/nnclr.py ran fingerprinted MIT (permissive) · f4dca3b21591894a · report fixture: returned NNCLR · level recorded 2026-09-22
NNCLRPredictionHead lightly/models/nnclr.py ran MIT (permissive) · c86c2eda640e0f05 · report fixture: returned NNCLRPredictionHead · level recorded 2026-09-22
NNCLRProjectionHead lightly/models/nnclr.py ran MIT (permissive) · b23b111c2f4e00fd · report fixture: returned NNCLRProjectionHead · level recorded 2026-09-22

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 Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR) (graph method: Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR)). 2 bricks; individually on a fixture: 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. NNCLR entry · level 0 · unverified · a8d39573526af033
  2. ContrastiveModel helper · level 1 · ran · acc020a5fafd0a3c

harvested Assembly for Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR) (graph method: Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR)). 4 bricks; individually on a fixture: 4 ran (of which 4 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) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. NNCLR entry · level 1 · ran · f4dca3b21591894a
  2. NNCLRPredictionHead helper · level 1 · ran · c86c2eda640e0f05
  3. NNCLRProjectionHead helper · level 1 · ran · b23b111c2f4e00fd
  4. ProjectionHead helper · level 1 · ran · da76a8285671b345

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="2104.14548") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningFine-Grained Image ClassificationImage ClassificationSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification Birdsnap NNCLR Accuracy 61.4% #5 of 5 Archive leaderboard report
Fine-Grained Image Classification Caltech-101 NNCLR Top-1 Error Rate 8.7% #9 of 18 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft NNCLR Accuracy 64.1 #53 of 57 Archive leaderboard report
Fine-Grained Image Classification SUN397 NNCLR Accuracy 62.5 #5 of 5 Archive leaderboard report
Image Classification CIFAR-10 NNCLR Percentage correct 93.7 #172 of 265 Archive leaderboard report
Image Classification CIFAR-100 NNCLR Percentage correct 79 #135 of 211 Archive leaderboard report
Image Classification DTD NNCLR Accuracy 75.5 #10 of 11 Archive leaderboard report
Image Classification Flowers-102 NNCLR Accuracy 95.1 #43 of 52 Archive leaderboard report
Image Classification Food-101 NNCLR Accuracy (%) 76.7 #10 of 11 Archive leaderboard report
Image Classification Oxford-IIIT Pet Dataset NNCLR Accuracy 91.8 #3 of 5 Archive leaderboard report
Image Classification PASCAL VOC 2007 NNCLR Accuracy 83 #1 of 1 Archive leaderboard report
Image Classification Stanford Cars NNCLR Accuracy 67.1 #24 of 24 Archive leaderboard report
Self-Supervised Image Classification ImageNet NNCLR (ResNet-50, multi-crop) Number of Params 25M #71 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet NNCLR (ResNet-50, multi-crop) Top 1 Accuracy 75.6% #71 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet NNCLR (ResNet-50, multi-crop) Top 5 Accuracy 92.4 #71 of 144 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data NNCLR (ResNet-50) Top 1 Accuracy 56.4% #44 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data NNCLR (ResNet-50) Top 5 Accuracy 80.7 #44 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data NNCLR (ResNet-50) Top 1 Accuracy 69.8% #40 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data NNCLR (ResNet-50) Top 5 Accuracy 89.3 #40 of 75 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

Introduced by this paper: NNCLR

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterContrastive LearningConvolutionDense ConnectionsGlobal Average PoolingKaiming InitializationMax PoolingNNCLRRandom Resized CropReLUResidual BlockResidual ConnectionSupervised Contrastive Loss

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