Papers › Revisiting Self-Supervised Visual Representation Learning

Revisiting Self-Supervised Visual Representation Learning

25 Jan 2019CVPR 2019 6arXiv:1901.09005archive 2025-07-28

Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging benchmarks. A large number of the pretext tasks for self-supervised learning have been studied, but other important aspects, such as the choice of convolutional neural networks (CNN), has not received equal attention. Therefore, we revisit numerous previously proposed self-supervised models, conduct a thorough large scale study and, as a result, uncover multiple crucial insights. We challenge a number of common practices in selfsupervised visual representation learning and observe that standard recipes for CNN design do not always translate to self-supervised representation learning. As part of our study, we drastically boost the performance of previously proposed techniques and outperform previously published state-of-the-art results by a large margin.

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 15 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 7 samples from 1 repository, 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google/revisiting-self-supervised officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
moabitcoin/ssvr mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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); 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
rickyHong/Puzzle-tensorflow-latest-repl mentioned on GitHubtfApache-2.0Syntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
rkorzeniowski/bigbigan-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large Scale Adversarial Representation Learning (arXiv:1907.02544; that paper's own run record: 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) · 1 unverified); nothing checks that they implement this paper's method. report
virtualgraham/sc_patch 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); 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

15 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 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.

9ran
6unverified

Licence: 7 of the 15 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.

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.

google/revisiting-self-supervised official repository 8 samples, 5 ran (0 instrument-failed) · 3 unverified
fixed_padding in 28 papers models/resnet.py ran fingerprinted Apache-2.0 (permissive) · 650804f0bf60d727 · report fixture: signature x:EagerTensor/4/float, kernel_size:int/0/int · returned EagerTensor · level recorded 2026-09-25
generate_sharded_filenames datasets.py ran Apache-2.0 (permissive) · 67c0ff3ae27aa20b · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-25
get_shape_as_list models/resnet.py ran Apache-2.0 (permissive) · f3176d55b81052d5 · report fixture: signature x:EagerTensor/2/float · returned list · level recorded 2026-09-25
image_grid in 41 papers self_supervision/patch_utils.py ran Apache-2.0 (permissive) · 8f93014aa9fd5d3f · report fixture: returned EagerTensor · level recorded 2026-09-25
repeat in 22 papers self_supervision/exemplar.py ran Apache-2.0 (permissive) · 0e9af15ef7691776 · report fixture: signature x:EagerTensor/1/int, times:int/0/int · returned EagerTensor · level recorded 2026-09-25
batch_norm in 46 papers models/resnet.py unverified Apache-2.0 (permissive) · d29f9171cd72ee14 · report
image_to_patches self_supervision/patch_model_preprocess.py unverified Apache-2.0 (permissive) · d6adc3a769d03202 · report
rickyHong/Puzzle-tensorflow-latest-repl community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
adaptive_pool utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · a758b93f9c0566d4 · report fixture: signature inp:EagerTensor/4/float, num_target_dimensions:int/0/int, mode:str/0/str · returned EagerTensor · level recorded 2026-09-24
concat_dicts utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 4fdb7cc6673fd054 · report fixture: signature dict_list:list/1/dict · returned defaultdict · level recorded 2026-09-24
get_resize_small preprocess.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · f2ead8be8bb7d21c · report fixture: signature smaller_size:int/0/int · returned function · level recorded 2026-09-24
str2intlist utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 420d7fad13c47138 · report fixture: signature s:str/0/str, repeats_if_single:NoneType/0/? · returned list · level recorded 2026-09-24
convbnrelu models/vggnet.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 1b8fc1e32b1ff09f · report
get_lr in 91 papers trainer.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · baf26176db8e0350 · report
vgg19 in 10 papers models/vggnet.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 5f17db2cd3b2b06d · report

Tasks

Representation LearningSelf-Supervised Image ClassificationSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet Revisited Rotation (RevNet-50 ×4) Number of Params 86M #130 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Rotation (RevNet-50 ×4) Top 1 Accuracy 55.4% #130 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Rotation (RevNet-50 ×4) Top 5 Accuracy 77.9% #130 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Rel.Patch.Loc (ResNet50 ×2) Number of Params 94M #132 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Rel.Patch.Loc (ResNet50 ×2) Top 1 Accuracy 51.4% #132 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Rel.Patch.Loc (ResNet50 ×2) Top 5 Accuracy 74.0% #132 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Exemplar (ResNet-50 ×3) Number of Params 211M #135 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Exemplar (ResNet-50 ×3) Top 1 Accuracy 46.0% #135 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Exemplar (ResNet-50 ×3) Top 5 Accuracy 68.8% #135 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Jigsaw (ResNet50 ×2) Number of Params 94M #136 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Jigsaw (ResNet50 ×2) Top 1 Accuracy 44.6% #136 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Revisited Jigsaw (ResNet50 ×2) Top 5 Accuracy 68.0% #136 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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