Papers › Data-Efficient Image Recognition with Contrastive Predictive Coding

Data-Efficient Image Recognition with Contrastive Predictive Coding

22 May 2019ICML 2020 1arXiv:1905.09272archive 2025-07-28

Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification with deep neural networks, this representation allows us to use 2-5x less labels than classifiers trained directly on image pixels. Finally, this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 2 repositories linked to this paper: 2 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; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 2 samples from 2 repositories, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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

SeonghoBaek/CPC mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
SeonghoBaek/FrameSequencePrediction mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mf1024/Contrastive-Predictive-Coding-for-Image-Recognition-in-PyTorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Representation Learning with Contrastive Predictive Coding (arXiv:1807.03748; that paper's own run record: 35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
philip-bachman/amdim-public mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Representations by Maximizing Mutual Information Across Views (arXiv:1906.00910; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 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

2 samples harvested: 2 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; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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

Licence: 2 of the 2 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”. “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.

SeonghoBaek/CPC community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
prepare_patches cpc.py ran · our draft was wrong no licence file found · pointer only · 9fe2e9df8b439589 · report fixture: signature image:ndarray/3/float, patch_size:list/1/int, patch_dim:list/1/int, stride:int/0/int · returned ndarray · level recorded 2026-09-22
SeonghoBaek/FrameSequencePrediction community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_global_context_area FSPNet.py ran · our draft was wrong no licence file found · pointer only · c247378c1de06222 · report fixture: signature img:ndarray/2/int, area:list/1/int · returned ndarray · level recorded 2026-09-22

Tasks

Contrastive LearningGeneral ClassificationObject DetectionSelf-Supervised Image ClassificationSemi-Supervised Image ClassificationTransfer Learningobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Contrastive Learning imagenet-1k ResNet50 (v2) ImageNet Top-1 Accuracy 63.8 #6 of 14 Archive leaderboard report
Contrastive Learning imagenet-1k ResNet v2 101 ImageNet Top-1 Accuracy 48.7 #14 of 14 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v2) Number of Params 305M #98 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v2) Top 1 Accuracy 71.5% #98 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v2) Top 5 Accuracy 90.1% #98 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-50) (arxiv v2) Number of Params 24M #115 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-50) (arxiv v2) Top 1 Accuracy 63.8% #115 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-50) (arxiv v2) Top 5 Accuracy 85.3% #115 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v1) Number of Params 305M #121 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v1) Top 1 Accuracy 61.0% #121 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CPC v2 (ResNet-161) (arxiv v1) Top 5 Accuracy 83.0% #121 of 144 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data CPC v2 (ResNet-161) Top 1 Accuracy 73.1% #37 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data CPC v2 (ResNet-161) Top 5 Accuracy 91.2% #37 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: CPC v2

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBottleneck Residual BlockCPC v2Contrastive Predictive CodingConvolutionDropoutFaster R-CNNGlobal Average PoolingInfoNCEKaiming InitializationLayer NormalizationMax PoolingRPNRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionRoIPoolSoftmaxWeight Decay

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