Papers › Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Jure Zbontar, Li Jing, Ishan Misra, Yann Lecun, Stéphane Deny
Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant solutions. Most current methods avoid such solutions by careful implementation details. We propose an objective function that naturally avoids collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and making it as close to the identity matrix as possible. This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors. The method is called Barlow Twins, owing to neuroscientist H. Barlow's redundancy-reduction principle applied to a pair of identical networks. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. Intriguingly it benefits from very high-dimensional output vectors. Barlow Twins outperforms previous methods on ImageNet for semi-supervised classification in the low-data regime, and is on par with current state of the art for ImageNet classification with a linear classifier head, and for transfer tasks of classification and object detection.
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.
Syntology holds a reference implementation of BARLOW TWINS, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='BARLOW TWINS') (how to connect); the free check have('2103.03230') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2103.03230")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2103.03230", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2103.03230")
Code
Syntology 26 code samples harvested from 16 repositories linked to this paper: 21 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 23 samples from 13 repositories, 19 ran (15 with no instrument failure; 4 where Syntology's instrument failed); community: 2 samples from 2 repositories, 1 ran (0 with no instrument failure; 1 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 5 of its repositories that Syntology harvested for other papers:
- Westlake-AI/openmixup, community (archive-listed): harvested for 4 other papers, listed under the repository
- facebookresearch/vissl, community (archive-listed): harvested for 4 other papers, listed under the repository
- jonahanton/ssl_audio, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmselfsup, community (archive-listed): harvested for another paper, listed under the repository
- vturrisi/solo-learn, community (archive-listed): harvested for 3 other papers, listed under the repository
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. 2 of the 21 samples that ran have no recorded date.
24 repositories listed; official and paper-mentioned ones first.
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
26 samples harvested: 21 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 5 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.
Licence: 10 of the 26 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 16 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”. For 3 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.
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket evaluate.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) ·
b0f936d4d6ae3b8c · report
fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded, date not recorded 252dd592b0af15de · report
fixture: returned BarlowTwins · level recorded 2026-09-22 3849a604087cfc40 · report
fixture: returned MLP · level recorded 2026-09-22 158c8987347b3ecf · report
fixture: signature z_a:Tensor/2/float, z_b:Tensor/2/float · returned Tensor · level recorded 2026-09-22 7c1ae63680739389 · report
fixture: returned BarlowTwins · level recorded 2026-09-22 814473a28a9616d7 · report
fixture: returned NetWrapper · level recorded 2026-09-22 0001a7e1fc3c2810 · report
b91cd63620b31f22 · report
fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket barlow_twins/loss.py ran · violated contract no licence file found · pointer only ·
bba1fbd383276faa · report
fixture: signature z1:EagerTensor/2/float, z2:EagerTensor/2/float, _lambda:float/0/float, global_batch_size:int/0/int · returned EagerTensor · level recorded 2026-09-22 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket barlow_twins/loss.py ran · honoured contract fingerprinted no licence file found · pointer only ·
36fab4f0e7dc9d33 · report
fixture: signature x:EagerTensor/2/float, eps:float/0/float · returned EagerTensor · level recorded 2026-09-22 c7572ab85515d03b · report
fixture: returned BarlowTwin · level recorded 2026-09-22 72c346ee974adb6e · report
fixture: returned Sequential · level recorded 2026-09-22 e2109c17551bb49d · report
fixture: signature in_dims:int/0/int, out_dims:int/0/int · returned Sequential · level recorded 2026-09-22 f7168ce264a363d3 · report
e1c7432eaf01c11e · report
fixture: returned BarlowTwins · level recorded 2026-09-22 659ab61af5f11edd · report
fixture: signature z_a:Tensor/2/float, z_b:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 6 implementations from 6 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 lightly/loss/barlow_twins_loss.py ran · our draft was wrong fingerprinted MIT (permissive) ·
693d992853ac438d · report
fixture: signature z:Tensor/2/float · returned Tensor · level recorded 2026-09-22 9b199e6e012c6948 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 d799236e3db12e5f · report
fixture: signature z1:Tensor/2/float, z2:Tensor/2/float, batch_size:int/0/int, scale_loss:float/0/float, lambd:float/0/float · returned Tensor · level recorded 2026-09-22 e9f736b6b3acb5d1 · report
fixture: signature z1:Tensor/2/float, z2:Tensor/2/float · returned Tensor · level recorded 2026-09-22 666e333d72371dc9 · report
fixture: signature x1:Tensor/4/float, x2:Tensor/4/float · returned Tensor · level recorded 2026-09-24 d3607edd155cc1dc · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 87987d8832a7303f · report
f2cfbed090a22f9d · report
fixture: signature h1:Tensor/2/float, h2:Tensor/2/float, lambda_:float/0/float, batch_norm:bool/0/bool, eps:float/0/float · returned Tensor · level recorded, date not recorded 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
14 assemblies on this paper: 13 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).
generated Assembly for BARLOW TWINS (graph method: BARLOW TWINS), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.
label matches by construction: the code was generated for this method (not judged by a model)
- barlow_twins_loss entry · level 3 · ran · violated contract ·
e1505111309e1113b3dd156dd079225464d0a782a1c3317bc4b693e72326b37f
13 sibling assemblies for BARLOW TWINS (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 13 sibling assemblies; the other 1 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwins entry · level 1 · ran ·
e1c7432eaf01c11e
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 2 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwins entry · level 0 · unverified ·
0001a7e1fc3c2810 - ContrastiveModel helper · level 1 · ran ·
acc020a5fafd0a3c
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwin entry · level 1 · ran ·
c7572ab85515d03b - get_backbone model · level 1 · ran ·
72c346ee974adb6e - projector model · level 1 · ran · our draft was wrong ·
e2109c17551bb49d
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 2 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwinsLoss entry · level 1 · ran · our draft was wrong ·
d799236e3db12e5f - off_diagonal helper · level 1 · ran; the contract check could not run ·
3e30d88eaef01190
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 2 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) · 0 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 13 siblings
- BarlowTwins entry · level 1 · ran ·
252dd592b0af15de - MLP helper · level 1 · ran ·
3849a604087cfc40
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwins entry · level 1 · ran ·
7c1ae63680739389 - NetWrapper helper · level 1 · ran ·
814473a28a9616d7 - off_diagonal helper · level 1 · ran; the contract check could not run ·
3e30d88eaef01190 - flatten helper · level 1 · ran · honoured contract ·
4daa3e876f494d75
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 13 siblings
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- barlow_twins_train entry · level 0 · unverified ·
f7168ce264a363d3
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 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 13 siblings
- BarlowTwinsLoss entry · level 1 · ran ·
158c8987347b3ecf
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwinsLoss entry · level 1 · ran ·
e9f736b6b3acb5d1 - off_diagonal helper · level 1 · ran; the contract check could not run ·
3e30d88eaef01190
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwinsLoss entry · level 1 · ran ·
659ab61af5f11edd - _normalize helper · level 1 · ran · our draft was wrong ·
693d992853ac438d - _off_diagonal helper · level 1 · ran; the contract check could not run (RAISES) ·
9b199e6e012c6948
harvested Assembly for BARLOW TWINS (graph method: BARLOW TWINS). 5 bricks; individually on a fixture: 4 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; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 13 siblings
- BarlowTwins entry · level 1 · ran ·
666e333d72371dc9 - BaseMethod helper · level 0 · unverified ·
87987d8832a7303f - ResNetBackbone helper · level 1 · ran ·
d3607edd155cc1dc - off_diagonal helper · level 1 · ran; the contract check could not run ·
3e30d88eaef01190 - _get_weights_url helper · level 1 · ran · our draft was wrong ·
589ff9232fa952cc
- BARLIP · fffe18394f897988 · 10 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
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="2103.03230") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
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: Barlow Twins
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