Papers › Unsupervised visualization of image datasets using contrastive learning

Unsupervised visualization of image datasets using contrastive learning

18 Oct 2022arXiv:2210.09879archive 2025-07-28

Jan Niklas Böhm, Philipp Berens, Dmitry Kobak

Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are widely used for visualizing high-dimensional data. Yet, these approaches only produce meaningful results if the nearest neighbors themselves are meaningful. For images represented in pixel space this is not the case, as distances in pixel space are often not capturing our sense of similarity and therefore neighbors are not semantically close. This problem can be circumvented by self-supervised approaches based on contrastive learning, such as SimCLR, relying on data augmentation to generate implicit neighbors, but these methods do not produce two-dimensional embeddings suitable for visualization. Here, we present a new method, called t-SimCNE, for unsupervised visualization of image data. T-SimCNE combines ideas from contrastive learning and neighbor embeddings, and trains a parametric mapping from the high-dimensional pixel space into two dimensions. We show that the resulting 2D embeddings achieve classification accuracy comparable to the state-of-the-art high-dimensional SimCLR representations, thus faithfully capturing semantic relationships. Using t-SimCNE, we obtain informative visualizations of the CIFAR-10 and CIFAR-100 datasets, showing rich cluster structure and highlighting artifacts and outliers.

PaperPDFCodeCode 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 34 code samples harvested from 1 repository linked to this paper: 30 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 34 samples from 1 repository, 30 ran (18 with no instrument failure; 12 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

berenslab/t-simcne officialmentioned in papermentioned on GitHubpytorchSyntology: 34 samples, 30 ran (12 instrument-failed) · 4 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.

Code Syntology ran Syntology

34 samples harvested: 30 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 12 where Syntology's instrument failed) · 4 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.

11ran · our draft was wrong
1ran; the contract check could not run
18ran
4unverified

Licence: 34 of the 34 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 berenslab/t-simcne. “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 8 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.

berenslab/t-simcne official repository 34 samples, 30 ran (12 instrument-failed) · 4 unverified
AdaptedConvNet tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · 10e1c4c808c2af91 · report fixture: returned AdaptedConvNet · level recorded 2026-09-22
AnnoyClassifier tsimcne/tsimcne.py ran no licence file found · pointer only · 1da1a6199e752860 · report fixture: returned AnnoyClassifier · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · 708ad087bed51791 · report fixture: returned BasicBlock · level recorded 2026-09-22
Bottleneck in 98 papers tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · a8a906a8df4debd7 · report fixture: returned Bottleneck · level recorded 2026-09-22
CauchyTemp tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · e8a2a9d7d1eed11f · report fixture: signature features:Tensor/2/float · returned dict · level recorded 2026-09-24
ConstantSchedule tsimcne/tsimcne.py ran no licence file found · pointer only · 28b3eec38bdb1aa8 · report fixture: returned ConstantSchedule · level recorded 2026-09-22
ContrastiveFC tsimcne/tsimcne.py ran no licence file found · pointer only · cebb09009b18e10f · report fixture: returned ContrastiveFC · level recorded 2026-09-22
CosineAnnealingSchedule tsimcne/tsimcne.py ran no licence file found · pointer only · 8830446219159f10 · report fixture: returned CosineAnnealingSchedule · level recorded 2026-09-22
CosineTemp tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · 66f59e96941c4d9d · report fixture: returned CosineTemp · level recorded 2026-09-22
FCNetwork tsimcne/tsimcne.py ran no licence file found · pointer only · adb35fe02169f86f · report fixture: returned FCNetwork · level recorded 2026-09-22
InfoNCECauchy tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · ff0e5d779bcc673c · report fixture: returned InfoNCECauchy · level recorded 2026-09-22
InfoNCECosine tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · 15926b4f59f756c0 · report fixture: returned InfoNCECosine · level recorded 2026-09-22
InfoNCEGaussian tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · a808f763175bd0fa · report fixture: returned InfoNCEGaussian · level recorded 2026-09-22
InfoNCET tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · 441018b52d5d74f6 · report fixture: signature features:Tensor/2/float · returned dict · level recorded 2026-09-24
LinearSchedule tsimcne/tsimcne.py ran no licence file found · pointer only · f4b91fb2a716c3c2 · report fixture: returned LinearSchedule · level recorded 2026-09-22
ResNet in 139 papers tsimcne/tsimcne.py ran fingerprinted no licence file found · pointer only · c1a15ec76e903086 · report fixture: signature x:Tensor/4/float, layer:int/0/int · returned Tensor · level recorded 2026-09-24
TransformedPairDataset tsimcne/tsimcne.py ran no licence file found · pointer only · 0884dbb028cc4bc2 · report fixture: returned TransformedPairDataset · level recorded 2026-09-22
efficientnet_v2_l tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · acde91eeb9d55da8 · report fixture: signature in_channel:int/0/int · returned AdaptedConvNet · level recorded 2026-09-22
efficientnet_v2_m tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · 9ba5e8de3d6c4784 · report fixture: signature in_channel:int/0/int, weights:NoneType/0/?, progress:bool/0/bool · returned AdaptedConvNet · level recorded 2026-09-22
efficientnet_v2_s tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · fd6897a2da6f5e74 · report fixture: signature in_channel:int/0/int · returned AdaptedConvNet · level recorded 2026-09-22
get_transforms_unnormalized tsimcne/tsimcne.py ran; the contract check could not run (DEP_MISSING) no licence file found · pointer only · 9c92a074b1808e07 · report fixture: signature size:int/0/int, setting:str/0/str, crop_scale_lo:float/0/float, crop_scale_hi:float/0/float, use_ffcv:bool/0/bool · returned Compose · level recorded 2026-09-22
make_projection_head tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · e553d58b96b7ba40 · report fixture: signature name:str/0/str, in_dim:int/0/int, hidden_dim:int/0/int, out_dim:int/0/int · returned FCNetwork · level recorded 2026-09-22
mobilenet_v3_large tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · a69f355cbc16555b · report fixture: signature in_channel:int/0/int · returned AdaptedConvNet · level recorded 2026-09-22
mobilenet_v3_small tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · a4ac86aba2745847 · report fixture: signature in_channel:int/0/int · returned AdaptedConvNet · level recorded 2026-09-22
mutate_model tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · 5eb80a31c97779f3 · report fixture: signature model:callable/0/?, change:str/0/str, freeze:NoneType/0/?, proj_head:str/0/str, out_dim:int/0/int, hidden_dim:NoneType/0/?, last_lin_std:float/0/float · returned MinimalModel · level recorded 2026-09-22
pytorch_resnet tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · 2a7f005563b3d9c5 · report fixture: signature in_channel:int/0/int · returned ResNet · level recorded 2026-09-22
resnet101 in 24 papers tsimcne/tsimcne.py ran no licence file found · pointer only · a86999ce90809772 · report fixture: returned ResNet · level recorded 2026-09-22
resnet18 in 432 papers tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · 9fa1f1002d0b7031 · report fixture: signature in_channel:int/0/int, zero_init_residual:bool/0/bool · returned ResNet · level recorded 2026-09-22
resnet34 in 148 papers tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · b76d3a708d1bd1b0 · report fixture: signature in_channel:int/0/int, zero_init_residual:bool/0/bool · returned ResNet · level recorded 2026-09-22
resnet50 in 121 papers tsimcne/tsimcne.py ran · our draft was wrong no licence file found · pointer only · 02e8b84269fc9d6e · report fixture: signature in_channel:int/0/int, zero_init_residual:bool/0/bool · returned ResNet · level recorded 2026-09-22
PLtSimCNE tsimcne/tsimcne.py unverified no licence file found · pointer only · d7d6362fc17d9a63 · report
ResNetFC tsimcne/tsimcne.py unverified no licence file found · pointer only · adf91ee454b6330f · report
TSimCNE tsimcne/tsimcne.py unverified no licence file found · pointer only · a5b6863b8b2849a8 · report
make_model in 37 papers tsimcne/tsimcne.py unverified no licence file found · pointer only · a6be304389f8001d · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for t-SimCNE (graph method: t-SimCNE). 34 bricks; individually on a fixture: 30 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. TSimCNE entry · level 0 · unverified · a5b6863b8b2849a8
  2. PLtSimCNE helper · level 0 · unverified · d7d6362fc17d9a63
  3. TransformedPairDataset helper · level 1 · ran · 0884dbb028cc4bc2
  4. get_transforms_unnormalized helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 9c92a074b1808e07
  5. mutate_model helper · level 1 · ran · our draft was wrong · 5eb80a31c97779f3
  6. AnnoyClassifier metric · level 1 · ran · 1da1a6199e752860
  7. CauchyTemp helper · level 1 · ran · e8a2a9d7d1eed11f
  8. ConstantSchedule helper · level 1 · ran · 28b3eec38bdb1aa8
  9. CosineAnnealingSchedule helper · level 1 · ran · 8830446219159f10
  10. CosineTemp helper · level 1 · ran · 66f59e96941c4d9d
  11. InfoNCECauchy helper · level 1 · ran · ff0e5d779bcc673c
  12. InfoNCECosine loss · level 1 · ran · 15926b4f59f756c0
  13. InfoNCEGaussian loss · level 1 · ran · a808f763175bd0fa
  14. LinearSchedule helper · level 1 · ran · f4b91fb2a716c3c2
  15. make_model model · level 0 · unverified · a6be304389f8001d
  16. make_projection_head model · level 1 · ran · our draft was wrong · e553d58b96b7ba40
  17. InfoNCET loss · level 1 · ran · 441018b52d5d74f6
  18. ContrastiveFC model · level 1 · ran · cebb09009b18e10f
  19. ResNetFC model · level 0 · unverified · adf91ee454b6330f
  20. FCNetwork model · level 1 · ran · adb35fe02169f86f
  21. AdaptedConvNet helper · level 1 · ran · 10e1c4c808c2af91
  22. BasicBlock helper · level 1 · ran · 708ad087bed51791
  23. Bottleneck helper · level 1 · ran · a8a906a8df4debd7
  24. ResNet helper · level 1 · ran · c1a15ec76e903086
  25. efficientnet_v2_l helper · level 1 · ran · our draft was wrong · acde91eeb9d55da8
  26. efficientnet_v2_m helper · level 1 · ran · our draft was wrong · 9ba5e8de3d6c4784
  27. efficientnet_v2_s helper · level 1 · ran · our draft was wrong · fd6897a2da6f5e74
  28. mobilenet_v3_large helper · level 1 · ran · our draft was wrong · a69f355cbc16555b
  29. mobilenet_v3_small helper · level 1 · ran · our draft was wrong · a4ac86aba2745847
  30. pytorch_resnet helper · level 1 · ran · our draft was wrong · 2a7f005563b3d9c5
  31. resnet101 helper · level 1 · ran · a86999ce90809772
  32. resnet18 helper · level 1 · ran · our draft was wrong · 9fa1f1002d0b7031
  33. resnet34 helper · level 1 · ran · our draft was wrong · b76d3a708d1bd1b0
  34. resnet50 helper · level 1 · ran · our draft was wrong · 02e8b84269fc9d6e

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="2210.09879") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningData Augmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterContrastive LearningConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingKaiming InitializationMax PoolingNT-XentRandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLR

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