Papers › DUET: 2D Structured and Approximately Equivariant Representations

DUET: 2D Structured and Approximately Equivariant Representations

28 Jun 2023arXiv:2306.16058archive 2025-07-28

Xavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, Luca Zappella

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.

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 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 9 ran (8 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.

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

apple/ml-duet officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 9 ran (1 instrument-failed) · 6 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

15 samples harvested: 9 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 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.

1ran · honoured contract
1ran · our draft was wrong
7ran
6unverified

Licence: 15 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 apple/ml-duet. “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 4 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.

apple/ml-duet official repository 15 samples, 9 ran (1 instrument-failed) · 6 unverified
BatchNormND duet/models/duet.py ran · metamorphic tier: deterministic licence not identified · pointer only · 1aae64bb00e30bb3 · report fixture: returned BatchNormND · level recorded 2026-09-22
Cifar10_ResNet duet/models/duet.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · c9aec5ed3baab71c · report fixture: returned Cifar10_ResNet · level recorded 2026-09-22
DUETLayer duet/models/duet.py ran · metamorphic tier: deterministic licence not identified · pointer only · bf58dc5e02638b17 · report fixture: returned DUETLayer · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
duet/models/duet.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 4f7e1c08346a6301 · report fixture: returned Identity · level recorded 2026-09-22
Squeezer duet/models/duet.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · f83957353db97231 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
View in 9 papers duet/models/duet.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 931e09f1354d129a · report fixture: returned View · level recorded 2026-09-22
aug_stack_from_codes duet/models/duet.py ran · our draft was wrong licence not identified · pointer only · a313ad3859803c5d · report fixture: signature codes:list/1/str · returned tuple · level recorded 2026-09-22
dummy_context duet/models/duet.py ran licence not identified · pointer only · afd70c94caa641e9 · report fixture: returned _GeneratorContextManager · level recorded 2026-09-22
get_aug_params duet/models/duet.py ran · honoured contract licence not identified · pointer only · 0b1813f686bf9dbf · report fixture: signature full_params:dict/0/?, groups:list/1/str · returned Tensor · level recorded 2026-09-22
DUET duet/models/duet.py unverified licence not identified · pointer only · 749d8932b36b065f · report
ParamAugStack duet/models/duet.py unverified licence not identified · pointer only · 99978a9ab1357a8c · report
RandomRotation90 duet/models/duet.py unverified licence not identified · pointer only · 40f59c42fe51876f · report
SimCLR duet/models/duet.py unverified licence not identified · pointer only · 6598676dc68f1a6f · report
_weights_init in 7 papers duet/models/duet.py unverified licence not identified · pointer only · b966d756f19409ce · report
augment_safe duet/models/duet.py unverified licence not identified · pointer only · 35c5c984a6f6af3a · 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 DUET (graph method: DUET). 15 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. DUET entry · level 0 · unverified · 749d8932b36b065f
  2. BatchNormND helper · level 1 · ran · 1aae64bb00e30bb3
  3. DUETLayer model · level 1 · ran · bf58dc5e02638b17
  4. ParamAugStack helper · level 0 · unverified · 99978a9ab1357a8c
  5. SimCLR helper · level 0 · unverified · 6598676dc68f1a6f
  6. augment_safe data_transform · level 0 · unverified · 35c5c984a6f6af3a
  7. get_aug_params helper · level 1 · ran · honoured contract · 0b1813f686bf9dbf
  8. RandomRotation90 helper · level 0 · unverified · 40f59c42fe51876f
  9. aug_stack_from_codes helper · level 1 · ran · our draft was wrong · a313ad3859803c5d
  10. Cifar10_ResNet helper · level 1 · ran · c9aec5ed3baab71c
  11. Squeezer helper · level 1 · ran · f83957353db97231
  12. dummy_context helper · level 1 · ran · afd70c94caa641e9
  13. Identity helper · level 1 · ran · 4f7e1c08346a6301
  14. View helper · level 1 · ran · 931e09f1354d129a
  15. _weights_init helper · level 0 · unverified · b966d756f19409ce

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="2306.16058") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Self-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionDense 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