Papers › Contrastive Multiview Coding

Contrastive Multiview Coding

13 Jun 2019ECCV 2020 8arXiv:1906.05849archive 2025-07-28

Yonglong Tian, Dilip Krishnan, Phillip Isola

Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important factors, such as physics, geometry, and semantics, tend to be shared between all views (e.g., a "dog" can be seen, heard, and felt). We investigate the classic hypothesis that a powerful representation is one that models view-invariant factors. We study this hypothesis under the framework of multiview contrastive learning, where we learn a representation that aims to maximize mutual information between different views of the same scene but is otherwise compact. Our approach scales to any number of views, and is view-agnostic. We analyze key properties of the approach that make it work, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views we learn from, the better the resulting representation captures underlying scene semantics. Our approach achieves state-of-the-art results on image and video unsupervised learning benchmarks. Code is released at: http://github.com/HobbitLong/CMC/.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1906.05849")

Code

Syntology Ran 3 of 4 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 3 samples from 1 repository, 2 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

HobbitLong/CMC officialmentioned in papermentioned on GitHubpytorchBSD-2-Clause report
SsnL/moco mentioned on GitHubpytorchNOASSERTION report
SsnL/moco_align_uniform mentioned on GitHubpytorchNOASSERTION report
danielchyeh/imagenet-100-pytorch mentioned on GitHubpytorchMIT report
szq0214/CMC_with_Image_Mixture mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

4 samples harvested; 3 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
1ran
1unverified

Licence: 1 of the 4 samples is 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 danielchyeh/imagenet-100-pytorch. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

accuracy danielchyeh/imagenet-100-pytorch/util.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · b0f936d4d6ae3b8c · report
set_optimizer danielchyeh/imagenet-100-pytorch/util.py community (archive-listed) ran MIT (permissive) · a44a1925c2c778ba · report
set_loader danielchyeh/imagenet-100-pytorch/main_IN100.py community (archive-listed) unverified MIT (permissive) · 78be23f19fa36f1c · report
set_optimizer identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 3267a33f67aebf53 · report

Tasks

Contrastive LearningSelf-Supervised Action RecognitionSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition UCF101 Contrastive Multiview Coding (CaffeNet x2) 3-fold Accuracy 59.1 #48 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 Contrastive Multiview Coding (CaffeNet x2) Frozen false #48 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 Contrastive Multiview Coding (CaffeNet x2) Pre-Training Dataset UCF101 #48 of 53 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50 x2) (arxiv v5) Number of Params 188M #102 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50 x2) (arxiv v5) Top 1 Accuracy 70.6% #102 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50 x2) (arxiv v5) Top 5 Accuracy 89.7% #102 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50) (arxiv v5) Number of Params 47M #110 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50) (arxiv v5) Top 1 Accuracy 66.2% #110 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-50) (arxiv v5) Top 5 Accuracy 87.0% #110 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-101) (arxiv v3) Top 1 Accuracy 65.0% #114 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-101) (arxiv v3) Top 5 Accuracy 86.0% #114 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-101) Number of Params 44M #127 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-101) Top 1 Accuracy 60.1% #127 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (ResNet-101) Top 5 Accuracy 82.8% #127 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (Alexnet/2) Number of Params 30M #137 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CMC (Alexnet/2) Top 1 Accuracy 42.6% #137 of 144 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: Contrastive Multiview Coding

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBottleneck Residual BlockContrastive Multiview CodingConvolutionDense ConnectionsDropoutGlobal Average PoolingGrouped ConvolutionInfoNCEKaiming InitializationLocal Response NormalizationMax PoolingRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionSGD with MomentumSoftmaxWeight 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