Papers › Momentum Contrast for Unsupervised Visual Representation Learning

Momentum Contrast for Unsupervised Visual Representation Learning

13 Nov 2019CVPR 2020 6arXiv:1911.05722archive 2025-07-28

Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

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

The archive's official repositories (facebookresearch/moco, ppwwyyxx/moco.tensorflow) were not harvested; the 42 samples below come from 24 community repositories.

Syntology 42 code samples harvested from 24 repositories linked to this paper: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 3 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: community (archive-listed): 42 samples from 24 repositories, 28 ran (23 with no instrument failure; 5 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 9 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. 2 of the 28 samples that ran have no recorded date.

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

facebookresearch/moco officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
ppwwyyxx/moco.tensorflow officialmentioned on GitHubtfSyntology: not harvested report
1170500804/MoCo mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
AidenDurrant/MoCo-Pytorch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
AndrewTal/MoCo-Pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
CoinCheung/denseCL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour (arXiv:1706.02677; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 4 unverified) and 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); nothing checks that they implement this paper's method. report
Evgeneus/MoCo mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
HobbitLong/CMC mentioned on GitHubpytorchBSD-2-ClauseSyntology: 6 samples, 5 ran (3 instrument-failed) · 1 unverified report
KevinMusgrave/pytorch-metric-learning mentioned on GitHubpytorchMITSyntology: not harvested report
KevinMusgrave/pytorch_metric_learning mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
LeiLiu-byte/the-Essence-of-LT-Rocognition mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
PaperCodeReview/MoCo-TF mentioned on GitHubtfMITSyntology: 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); nothing checks that they implement this paper's method. report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 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; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
YyzHarry/imbalanced-semi-self mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking the Value of Labels for Improving Class-Imbalanced Learning (arXiv:2006.07529; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
ali-nsua/DISCERN mentioned on GitHubpytorchSyntology: not harvested report
alihassanijr/DISCERN mentioned on GitHubpytorchSyntology: not harvested report
amazon-research/exponential-moving-average-normalization mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
beresandras/contrastive-classification-keras mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
bl0/moco mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
davidsvy/hard-negative-mixing mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ehsanik/muscleTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ernie1/pi-nas mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/vissl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (arXiv:1603.09246; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified), Unsupervised Representation Learning by Predicting Image Rotations (arXiv:1803.07728; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
giakoumoglou/synco mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
joshr17/IFM mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
kikacaty/adv_guide mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
leftthomas/moco mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
linwenye/light-moco mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
open-mmlab/mmselfsup mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling (arXiv:2303.02416; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
smartdanny/MoCoV2_CIFAR10 mentioned on GitHubpytorchSyntology: not harvested report
srinidhiPY/SSL_CR_Histo mentioned on GitHubpytorchSyntology: not harvested report
szq0214/CMC_with_Image_Mixture mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tranc012/SMILE-Rep mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
trannhiem/ma_ssrl_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
xiangli13/MoCo mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
zhangyifei01/EIR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
HobbitLong/PyContrast pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
PaddlePaddle/PASSL paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
Pangoraw/GeoSSL pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
giakou4/pyssl pytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/MoCo mindsporeSyntology: not harvested 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

42 samples harvested: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 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.

3ran · our draft was wrong
2ran; the contract check could not run
23ran
14unverified

Licence: 19 of the 42 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, 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 24 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 2 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.

1170500804/MoCo community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers moco/builder.py ran licence not identified · pointer only · 1f9e6eca512e3008 · report fixture: returned MoCo · level recorded 2026-09-22
AidenDurrant/MoCo-Pytorch community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
projection_MLP in 5 papers src/model/moco.py ran · metamorphic tier: deterministic no licence file found · pointer only · dc6a714ff10ed3d9 · report fixture: returned projection_MLP · level recorded 2026-09-22
MoCo_Model src/model/moco.py unverified no licence file found · pointer only · a70f3f9f550eb5c4 · report
AndrewTal/MoCo-Pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers moco/builder.py ran no licence file found · pointer only · d568cb5387bc22f3 · report fixture: returned MoCo · level recorded 2026-09-22
Evgeneus/MoCo community (archive-listed) 1 sample, 0 ran · 1 unverified
MoCo in 12 papers moco/builder.py unverified licence not identified · pointer only · 88df9e4db87f31e3 · report
HobbitLong/CMC community (archive-listed) 6 samples, 5 ran (3 instrument-failed) · 1 unverified
conv3x3 in 1,376 papers models/resnet.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
get_shuffle_ids in 9 papers train_moco_ins.py ran; the contract check could not run (RAISES) BSD-2-Clause (permissive) · e2e91e39d8368ced · report fixture: returned tuple · level recorded 2026-09-22
resnet18 in 432 papers models/resnet.py ran BSD-2-Clause (permissive) · e56061351deca46f · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
resnet34 in 148 papers models/resnet.py ran BSD-2-Clause (permissive) · f3aafd1c32c0381c · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
set_optimizer in 24 papers LinearProbing.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · 3267a33f67aebf53 · report fixture: signature args:Args/0/?, classifier:callable/0/? · returned SGD · level recorded, date not recorded
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
eval_moco_ins.py unverified BSD-2-Clause (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
KevinMusgrave/pytorch_metric_learning community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
ModuleWithRecords src/pytorch_metric_learning/losses/cross_batch_memory.py ran · metamorphic tier: deterministic MIT (permissive) · 5bf7745f1e480d55 · report fixture: returned ModuleWithRecords · level recorded 2026-09-22
BaseLossWrapper src/pytorch_metric_learning/losses/cross_batch_memory.py unverified MIT (permissive) · 3576e4fdf9ea3c2e · report
CrossBatchMemory src/pytorch_metric_learning/losses/cross_batch_memory.py unverified MIT (permissive) · f5b8b2ab5c47caa7 · report
amazon-research/exponential-moving-average-normalization community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
MoCo in 12 papers models/moco.py ran · metamorphic tier: deterministic no licence file found · pointer only · 60e7c290602e7d6a · report fixture: returned MoCo · level recorded 2026-09-22
build_hidden_head models/moco.py ran · our draft was wrong no licence file found · pointer only · 3ce0bcff10714b54 · report fixture: signature num_mlp:int/0/int, dim_mlp:int/0/int, dim:int/0/int · returned Sequential · level recorded 2026-09-22
beresandras/contrastive-classification-keras community (archive-listed) 2 samples, 0 ran · 2 unverified
MoCo in 12 papers algorithms.py unverified MIT (permissive) · 1318e70df1366b7a · report
MomentumContrastiveModel algorithms.py unverified MIT (permissive) · 521294b5f41beba8 · report
bl0/moco community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MemoryMoCo moco/NCE/Contrast.py ran no licence file found · pointer only · dfdbae86713f4677 · report fixture: signature q:Tensor/2/float, k:Tensor/2/float, k_all:Tensor/2/float · returned Tensor · level recorded 2026-09-24
davidsvy/hard-negative-mixing community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers src/moco.py ran MIT (permissive) · d0fb06c245f652b9 · report fixture: returned MoCo · level recorded 2026-09-22
ehsanik/muscleTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MemoryMoCo utils/contrastive_utils.py ran · metamorphic tier: deterministic no licence file found · pointer only · 587d6926bc87730f · report fixture: returned MemoryMoCo · level recorded 2026-09-22
giakoumoglou/synco community (archive-listed) 1 sample, 0 ran · 1 unverified
SynCo synco/builder.py unverified MIT (permissive) · 1fb0a31e12db1fbd · report
joshr17/IFM community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers moco-master/moco/builder.py ran · metamorphic tier: deterministic MIT (permissive) · a92f8d3efcd0fa73 · report fixture: returned MoCo · level recorded 2026-09-22
kikacaty/adv_guide community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers moco/builder.py ran licence not identified · pointer only · ce8d71b82b20b145 · report fixture: returned MoCo · level recorded 2026-09-22
leftthomas/moco community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Model in 227 papers model.py ran fingerprinted no licence file found · pointer only · 2e32520281111228 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
lightly-ai/lightly community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
MoCoProjectionHead lightly/models/moco.py ran MIT (permissive) · f0d8899a1cadcb6a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ProjectionHead in 10 papers lightly/models/moco.py ran MIT (permissive) · d76bde76567cd6c0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
MoCo in 12 papers lightly/models/moco.py unverified MIT (permissive) · 05ac8df2dc56ea0e · report
_MomentumEncoderMixin lightly/models/moco.py unverified MIT (permissive) · 40e7ae5bffc7ea30 · report
_deactivate_requires_grad lightly/models/moco.py unverified MIT (permissive) · 914a6024d62fcd9a · report
_do_momentum_update lightly/models/moco.py unverified MIT (permissive) · a44f04114cc14792 · report
linwenye/light-moco community (archive-listed) 1 sample, 0 ran · 1 unverified
MoCo in 12 papers moco/builder.py unverified licence not identified · pointer only · c605eb4989b100b9 · report
szq0214/CMC_with_Image_Mixture community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MemoryMoCo NCE/NCEAverage.py ran no licence file found · pointer only · 1b18a48a2e94a2b4 · report fixture: signature q:Tensor/2/float, k:Tensor/2/float · returned Tensor · level recorded 2026-09-24
trannhiem/ma_ssrl_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MomentumUpdater MA_SSRL/utils/momentum.py ran licence not identified · pointer only · d57c8e5463db2477 · report fixture: returned MomentumUpdater · level recorded 2026-09-22
xiangli13/MoCo community (archive-listed) 1 sample, 0 ran · 1 unverified
MoCo in 12 papers MoCo.py unverified MIT (permissive) · 766dfd5385bfa150 · report
zhangyifei01/EIR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MoCo in 12 papers moco/builder.py ran Apache-2.0 (permissive) · 6e34a9f59a466d7f · report fixture: returned MoCo · level recorded 2026-09-22
HobbitLong/PyContrast community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
BaseMoCo pycontrast/memory/mem_moco.py ran no licence file found · pointer only · 844eb6ac74b615e9 · report fixture: returned BaseMoCo · level recorded 2026-09-22
RGBMoCo pycontrast/memory/mem_moco.py ran fingerprinted no licence file found · pointer only · 205d8773b717c4eb · report fixture: returned RGBMoCo · level recorded 2026-09-22
Pangoraw/GeoSSL community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
CosineMomentumScheduler geossl/moco.py ran MIT (permissive) · bd4622df07c12c27 · report fixture: returned CosineMomentumScheduler · level recorded 2026-09-22
MoCo in 12 papers geossl/moco.py ran MIT (permissive) · 54ef0c846a171c93 · report fixture: returned MoCo · level recorded 2026-09-22
giakou4/pyssl community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
MoCo in 12 papers builders/moco.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 82980b2ad9007485 · report fixture: returned MoCo · level recorded 2026-09-22
infonce_loss in 5 papers builders/moco.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 5cd3d9e4fc246bdf · report fixture: signature q:Tensor/2/float, k:Tensor/2/float, queue:Tensor/2/float, temperature:float/0/float · returned Tensor · 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.

23 assemblies on this paper: 23 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

23 sibling assemblies for Momentum Contrast (MoCo) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 23 sibling assemblies; the other 11 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. MoCo entry · level 1 · ran · 82980b2ad9007485
  2. infonce_loss loss · level 1 · ran; the contract check could not run (RAISES) · 5cd3d9e4fc246bdf

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 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 23 siblings

  1. MoCo entry · level 1 · ran · a92f8d3efcd0fa73
  2. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 1 brick; 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) · 0 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 23 siblings

  1. MemoryMoCo entry · level 1 · ran · 587d6926bc87730f

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. SynCo entry · level 0 · unverified · 1fb0a31e12db1fbd
  2. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 3 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) · 2 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 23 siblings

  1. CrossBatchMemory entry · level 0 · unverified · f5b8b2ab5c47caa7
  2. BaseLossWrapper helper · level 0 · unverified · 3576e4fdf9ea3c2e
  3. ModuleWithRecords helper · level 1 · ran · 5bf7745f1e480d55

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 1 brick; individually on a fixture: 1 ran (of which 0 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 assembly has not been run end-to-end.

one of 23 siblings

  1. MemoryMoCo entry · level 1 · ran · dfdbae86713f4677

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 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 23 siblings

  1. MoCo_Model entry · level 0 · unverified · a70f3f9f550eb5c4
  2. projection_MLP model · level 1 · ran · dc6a714ff10ed3d9

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. MoCo entry · level 1 · ran · 60e7c290602e7d6a
  2. build_hidden_head helper · level 1 · ran · our draft was wrong · 3ce0bcff10714b54

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 3 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. MoCo entry · level 0 · unverified · c605eb4989b100b9
  2. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09
  3. softmax_cross_entropy_with_softtarget helper · level 1 · ran; the contract check could not run · 45dd43505b557df3

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 3 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) · 2 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 23 siblings

  1. MoCo entry · level 0 · unverified · 1318e70df1366b7a
  2. MomentumContrastiveModel model · level 0 · unverified · 521294b5f41beba8
  3. ContrastiveModel model · level 1 · ran · acc020a5fafd0a3c

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

one of 23 siblings

  1. RGBMoCo entry · level 1 · ran · 205d8773b717c4eb
  2. BaseMoCo helper · level 1 · ran · 844eb6ac74b615e9

harvested Assembly for Momentum Contrast (MoCo) (graph method: Momentum Contrast (MoCo)). 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 23 siblings

  1. MoCo entry · level 1 · ran · 1f9e6eca512e3008
  2. concat_all_gather helper · level 0 · unverified · 73cecca9f3575f09
  1. MoCo · 7218de0d624bfb65 · 1 brick; 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MomentumUpdater · 755ce53fc055525f · 1 brick; 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. MoCo · 791ad6fa6e05c7a0 · 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 · assemblies[14] in the JSON twin
  4. MoCo · 7bd3722f61373aef · 6 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. MoCo · 82e6ccee33bdb702 · 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 · assemblies[16] in the JSON twin
  6. MoCo · 9ac473daa2eb3ecc · 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. MoCo · b7675037d3c8efad · 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 · assemblies[18] in the JSON twin
  8. Model · c89334cce840017e · 1 brick; individually on a fixture: 1 ran (of which 0 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 assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. MoCo · d874e9ace27f2951 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. MemoryMoCo · dcfce87cebf49904 · 1 brick; individually on a fixture: 1 ran (of which 0 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 assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. MoCo · f2c690c08e79ad4f · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin

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="1911.05722") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningImage ClassificationRepresentation LearningSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Contrastive Learning imagenet-1k ResNet50 ImageNet Top-1 Accuracy 60.6 #11 of 14 Archive leaderboard report
Image Classification OmniBenchmark MoCoV2 Average Top-1 Accuracy 34.8 #14 of 22 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50 4x) Number of Params 375M #105 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50 4x) Top 1 Accuracy 68.6% #105 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50 2x) Number of Params 94M #112 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50 2x) Top 1 Accuracy 65.4% #112 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50) Number of Params 24M #123 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MoCo (ResNet-50) Top 1 Accuracy 60.6% #123 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MoCo (Resnet-50) Top 1 Accuracy 77.3% #62 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MoCo (Resnet-50) Top 1 Accuracy 77.0% #64 of 65 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionExponential DecayFPNFaster R-CNNGlobal Average PoolingInfoNCEKaiming InitializationMask R-CNNMax PoolingMoCoRPNRandom GrayscaleRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionRoIAlignRoIPoolSGD with MomentumSoftmax

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