Papers › Unsupervised Representation Learning by Predicting Image Rotations

Unsupervised Representation Learning by Predicting Image Rotations

21 Mar 2018ICLR 2018 1arXiv:1803.07728archive 2025-07-28

Spyros Gidaris, Praveer Singh, Nikos Komodakis

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised representation learning and thus significantly close the gap with supervised feature learning. For instance, in PASCAL VOC 2007 detection task our unsupervised pre-trained AlexNet model achieves the state-of-the-art (among unsupervised methods) mAP of 54.4% that is only 2.4 points lower from the supervised case. We get similarly striking results when we transfer our unsupervised learned features on various other tasks, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification. The code and models of our paper will be published on: https://github.com/gidariss/FeatureLearningRotNet .

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 22 code samples harvested from 11 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 21 samples from 10 repositories, 16 ran (14 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

gidariss/FeatureLearningRotNet officialmentioned in paperpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
Blimeo/rotnet mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
DamianValle/ScarceClassifier mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MixMatch: A Holistic Approach to Semi-Supervised Learning (arXiv:1905.02249; that paper's own run record: 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
JermXT/NMEPhw6 mentioned on GitHubpytorchSyntology: not harvested 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
PedroPachuca/project1 mentioned on GitHubtfSyntology: not harvested report
WaretleR/SelfSupervision mentioned on GitHubpytorchSyntology: not harvested 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
adham-elarabawy/nmep_proj1 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
adham-elarabawy/nn-rotation-predictor mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/vissl mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
k-han/AutoNovel mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
moabitcoin/ssvr mentioned on GitHubtfSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
nab-126/resnet mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 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
raghavjajodia/dsga1008_semisuperlearning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rahuldesai1/NMEP_HW5 mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified 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
zzz1515151/self-supervised_learning_sketch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Dylan-get/Feature-Learning-RotNet paddleApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified 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

22 samples harvested: 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. “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.

2ran · our draft was wrong
14ran
6unverified

Licence: 18 of the 22 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 11 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.

gidariss/FeatureLearningRotNet official repository 1 sample, 0 ran · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
algorithms/ClassificationModel.py unverified MIT (permissive) · f0c9a29156911331 · report
Blimeo/rotnet community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Data in 7 papers rotnet.py ran no licence file found · pointer only · 4d382e3a78bdf9d7 · report fixture: returned Data · level recorded 2026-09-22
ResNet in 139 papers rotnet.py ran no licence file found · pointer only · fd46a2a4889413f5 · report fixture: returned ResNet · level recorded 2026-09-22
RotNet rotnet.py unverified no licence file found · pointer only · 6901ba8acd00aef8 · report
adham-elarabawy/nmep_proj1 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RotNet rotnet.py ran · metamorphic tier: invariant no licence file found · pointer only · a60f48bb13f2d666 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
facebookresearch/vissl community (archive-listed) 1 sample, 0 ran · 1 unverified
AlexNetRotNet vissl/models/trunks/alexnet_rotnet.py unverified MIT (permissive) · a858acd790fe29c4 · report
k-han/AutoNovel community (archive-listed) 1 sample, 0 ran · 1 unverified
ResNet in 139 papers selfsupervised_learning.py unverified no licence file found · pointer only · 493987c2ab7c1620 · report
moabitcoin/ssvr community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
RotatedDataset ssvr/dataset.py ran no licence file found · pointer only · 2d3ead654fea6358 · report fixture: returned RotatedDataset · level recorded 2026-09-22
batched in 5 papers ssvr/dataset.py ran · our draft was wrong no licence file found · pointer only · 04648afad4671964 · report fixture: signature iterable:list/1/int, n:int/0/int · returned generator · level recorded 2026-09-22
files ssvr/dataset.py ran · our draft was wrong no licence file found · pointer only · 25b471b6747ae2ee · report fixture: signature path:PosixPath/0/? · returned generator · level recorded 2026-09-22
nab-126/resnet community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Data in 7 papers rotnet.py ran no licence file found · pointer only · 977eb64069f84f67 · report fixture: returned Data · level recorded 2026-09-22
ResNet in 139 papers rotnet.py ran no licence file found · pointer only · 7bbee0bfb7e65af2 · report fixture: returned ResNet · level recorded 2026-09-22
RotNet rotnet.py unverified no licence file found · pointer only · bf0ed0ecef689d4b · report
raghavjajodia/dsga1008_semisuperlearning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RotationDataset RotationLearning/RotationLearning.py ran fingerprinted no licence file found · pointer only · bdbea7111e28b11d · report fixture: signature idx:int/0/int · returned tuple · level recorded 2026-09-24
rahuldesai1/NMEP_HW5 community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Data in 7 papers rotnet.py ran no licence file found · pointer only · 0b75c3d1eaec7793 · report fixture: returned Data · level recorded 2026-09-22
ResNet in 139 papers rotnet.py ran no licence file found · pointer only · d7d646f8c811bb7f · report fixture: returned ResNet · level recorded 2026-09-22
RotNet rotnet.py unverified no licence file found · pointer only · 25c505aa05d2b385 · report
zzz1515151/self-supervised_learning_sketch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
AlexNet in 8 papers AlexNet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · da529ec59bbf59b8 · report fixture: signature x:Tensor/4/float, out_feat_keys:NoneType/0/? · returned Tensor · level recorded 2026-09-22
Flatten in 23 papers
census: 9 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
AlexNet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 89353fd06cc04c28 · report fixture: signature feat:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Dylan-get/Feature-Learning-RotNet community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
buildLabelIndex in 8 papers paddleRotNet/dataloader.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 57889d72f516d105 · report fixture: signature labels:list/1/int · returned dict · level recorded 2026-09-24
getConfMatrixResults paddleRotNet/utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 1c15c5f6cad99921 · report fixture: signature matrix:ndarray/2/float · returned dict · level recorded 2026-09-26
rotate_img in 7 papers paddleRotNet/dataloader.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 99bcaa01775e6c98 · report fixture: signature img:ndarray/3/float, rot:int/0/int · returned ndarray · level recorded 2026-09-26

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.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for predicting image rotations (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 3 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) · 1 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 9 siblings

  1. RotNet entry · level 0 · unverified · bf0ed0ecef689d4b
  2. Data helper · level 1 · ran · 977eb64069f84f67
  3. ResNet helper · level 1 · ran · 7bbee0bfb7e65af2

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 3 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) · 1 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 9 siblings

  1. RotNet entry · level 0 · unverified · 25c505aa05d2b385
  2. Data helper · level 1 · ran · 0b75c3d1eaec7793
  3. ResNet helper · level 1 · ran · d7d646f8c811bb7f

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RotatedDataset entry · level 1 · ran · 2d3ead654fea6358
  2. batched helper · level 1 · ran · our draft was wrong · 04648afad4671964
  3. files helper · level 1 · ran · our draft was wrong · 25b471b6747ae2ee

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 3 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) · 1 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 9 siblings

  1. RotNet entry · level 0 · unverified · 6901ba8acd00aef8
  2. Data helper · level 1 · ran · 4d382e3a78bdf9d7
  3. ResNet helper · level 1 · ran · fd46a2a4889413f5

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 6 bricks; individually on a fixture: 5 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. AlexNetRotNet entry · level 0 · unverified · a858acd790fe29c4
  2. AttrDict helper · level 1 · ran · 6663d33830e09bae
  3. Flatten helper · level 1 · ran · 0b750ebcd399df8e
  4. get_trunk_forward_outputs_module_list helper · level 1 · ran; the contract check could not run · b9b9733099ed93fd
  5. register_model_trunk helper · level 1 · ran · our draft was wrong · 4e819ea98b2a0bc8
  6. parse_out_keys_arg helper · level 1 · ran · our draft was wrong · fa8d202b59c77f16

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 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 9 siblings

  1. RotNet entry · level 1 · ran · a60f48bb13f2d666

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. ResNet entry · level 0 · unverified · 493987c2ab7c1620

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 2 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) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. AlexNet entry · level 1 · ran · da529ec59bbf59b8
  2. Flatten helper · level 1 · ran · 89353fd06cc04c28

harvested Assembly for predicting image rotations (graph method: predicting image rotations). 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 9 siblings

  1. RotationDataset entry · level 1 · ran · bdbea7111e28b11d

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="1803.07728") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

General ClassificationRepresentation LearningSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet Rotation (AlexNet) Number of Params 86M #140 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Rotation (AlexNet) Top 1 Accuracy 38.7 #140 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 ConvolutionConvolutionDense ConnectionsDropoutGrouped ConvolutionLocal Response NormalizationMax PoolingReLUSoftmax

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