Papers › Multiscale Deep Equilibrium Models

Multiscale Deep Equilibrium Models

15 Jun 2020NeurIPS 2020 12arXiv:2006.08656archive 2025-07-28

Shaojie Bai, Vladlen Koltun, J. Zico Kolter

We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An MDEQ directly solves for and backpropagates through the equilibrium points of multiple feature resolutions simultaneously, using implicit differentiation to avoid storing intermediate states (and thus requiring only O(1) memory consumption). These simultaneously-learned multi-resolution features allow us to train a single model on a diverse set of tasks and loss functions, such as using a single MDEQ to perform both image classification and semantic segmentation. We illustrate the effectiveness of this approach on two large-scale vision tasks: ImageNet classification and semantic segmentation on high-resolution images from the Cityscapes dataset. In both settings, MDEQs are able to match or exceed the performance of recent competitive computer vision models: the first time such performance and scale have been achieved by an implicit deep learning approach. The code and pre-trained models are at https://github.com/locuslab/mdeq .

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 14 code samples harvested from 4 repositories linked to this paper: 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) · 4 unverified. Where Syntology's instrument failed: 2 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: 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 3 repositories, 7 ran (4 with no instrument failure; 3 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.

locuslab/mdeq officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
SinclairHudson/DeepEquilibrium mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
locuslab/deq mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
lufanma/ifr mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 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

14 samples harvested: 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) · 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.

2ran · our draft was wrong
1ran; the contract check could not run
7ran
4unverified

Licence: 4 of the 14 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 4 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.

locuslab/mdeq official repository 4 samples, 3 ran (0 instrument-failed) · 1 unverified
BranchNet lib/models/mdeq_core.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 16eed3f65715e8e9 · report fixture: returned BranchNet · level recorded 2026-09-22
DownsampleModule lib/models/mdeq_core.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 68194e5af1ed3376 · report fixture: returned DownsampleModule · level recorded 2026-09-22
UpsampleModule lib/models/mdeq_core.py ran MIT (permissive) · 2b22e865b09bfe0c · report fixture: returned UpsampleModule · level recorded 2026-09-22
MDEQModule lib/models/mdeq_core.py unverified MIT (permissive) · 96aa0f0d7c9dc48a · report
SinclairHudson/DeepEquilibrium community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DEQ DEQ.py ran · metamorphic tier: deterministic no licence file found · pointer only · ecde83d001c2ad88 · report fixture: returned DEQ · level recorded 2026-09-22
locuslab/deq community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
DownsampleModule MDEQ-Vision/lib/models/mdeq_core.py ran fingerprinted MIT (permissive) · 94faf9823bec3580 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
UpsampleModule MDEQ-Vision/lib/models/mdeq_core.py ran · metamorphic tier: deterministic MIT (permissive) · f945eaf4c694d1fe · report fixture: returned UpsampleModule · level recorded 2026-09-22
WeightNorm MDEQ-Vision/lib/models/mdeq_core.py ran fingerprinted MIT (permissive) · 711a21f05476c8a1 · report fixture: returned WeightNorm · level recorded 2026-09-22
_norm MDEQ-Vision/lib/models/mdeq_core.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · a09788a6b90f7c7c · report fixture: signature p:Tensor/4/float, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-22
weight_norm in 14 papers MDEQ-Vision/lib/models/mdeq_core.py ran · our draft was wrong MIT (permissive) · a27206c36724f1c4 · report fixture: signature module:callable/0/?, names:list/1/str, dim:int/0/int · returned tuple · level recorded 2026-09-22
MDEQModule MDEQ-Vision/lib/models/mdeq_core.py unverified MIT (permissive) · 701031360acd0728 · report
lufanma/ifr community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
analyze_broyden lib/modules/deq2d.py ran · our draft was wrong no licence file found · pointer only · ed88fb917332b540 · report fixture: signature res_info:dict/0/?, err:dict/0/?, judge:bool/0/bool, name:str/0/str, training:bool/0/bool, save_err:bool/0/bool · returned tuple · level recorded 2026-09-24
DEQFunc2d lib/modules/deq2d.py unverified no licence file found · pointer only · 625bb3ec12707aaa · report
DEQModule2d lib/modules/deq2d.py unverified no licence file found · pointer only · bf6157640e178703 · 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. 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Multiscale Deep Equilibrium Model (MDEQ) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Multiscale Deep Equilibrium Model (MDEQ) (graph method: Multiscale Deep Equilibrium Model (MDEQ)). 7 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. MDEQModule entry · level 0 · unverified · 701031360acd0728
  2. BranchNet model · level 1 · ran · 16eed3f65715e8e9
  3. DownsampleModule model · level 1 · ran · 94faf9823bec3580
  4. UpsampleModule model · level 1 · ran · f945eaf4c694d1fe
  5. weight_norm helper · level 1 · ran · our draft was wrong · a27206c36724f1c4
  6. WeightNorm helper · level 1 · ran · 711a21f05476c8a1
  7. _norm helper · level 1 · ran; the contract check could not run (RAISES) · a09788a6b90f7c7c

harvested Assembly for Multiscale Deep Equilibrium Model (MDEQ) (graph method: Multiscale Deep Equilibrium Model (MDEQ)). 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 3 siblings

  1. DEQ entry · level 1 · ran · ecde83d001c2ad88

harvested Assembly for Multiscale Deep Equilibrium Model (MDEQ) (graph method: Multiscale Deep Equilibrium Model (MDEQ)). 9 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. DEQModule2d entry · level 0 · unverified · bf6157640e178703
  2. DEQFunc2d helper · level 0 · unverified · 625bb3ec12707aaa
  3. analyze_broyden helper · level 1 · ran · our draft was wrong · ed88fb917332b540
  4. broyden update_rule · level 1 · ran; the contract check could not run · ddffc87f2eef8c29
  5. line_search helper · level 1 · ran · our draft was wrong · cf5710371bcfb0ab
  6. matvec helper · level 1 · ran; the contract check could not run · ad49d989d6e115a5
  7. rmatvec helper · level 1 · ran · our draft was wrong · 968a8f446ad3c5b1
  8. _safe_norm helper · level 1 · ran · honoured contract · e2b1ac18e859c77f
  9. scalar_search_armijo helper · level 1 · ran · honoured contract · b2b5022f654ee4d3

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="2006.08656") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

General ClassificationImage ClassificationSegmentationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Multiscale DEQ (MDEQ-XL) Number of params 81M #771 of 1060 Archive leaderboard report
Image Classification ImageNet Multiscale DEQ (MDEQ-XL) Top 1 Accuracy 79.2% #771 of 1060 Archive leaderboard report
Semantic Segmentation Cityscapes val Multiscale DEQ (MDEQ-XL) mIoU 80.3% #54 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val Multiscale DEQ (MDEQ-large) mIoU 77.8% #63 of 99 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.

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