Papers › A ConvNet for the 2020s
A ConvNet for the 2020s
Zhuang Liu, Hanzi Mao, Chao-yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model. A vanilla ViT, on the other hand, faces difficulties when applied to general computer vision tasks such as object detection and semantic segmentation. It is the hierarchical Transformers (e.g., Swin Transformers) that reintroduced several ConvNet priors, making Transformers practically viable as a generic vision backbone and demonstrating remarkable performance on a wide variety of vision tasks. However, the effectiveness of such hybrid approaches is still largely credited to the intrinsic superiority of Transformers, rather than the inherent inductive biases of convolutions. In this work, we reexamine the design spaces and test the limits of what a pure ConvNet can achieve. We gradually "modernize" a standard ResNet toward the design of a vision Transformer, and discover several key components that contribute to the performance difference along the way. The outcome of this exploration is a family of pure ConvNet models dubbed ConvNeXt. Constructed entirely from standard ConvNet modules, ConvNeXts compete favorably with Transformers in terms of accuracy and scalability, achieving 87.8% ImageNet top-1 accuracy and outperforming Swin Transformers on COCO detection and ADE20K segmentation, while maintaining the simplicity and efficiency of standard ConvNets.
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):
get_harvested_code_for_paper(arxiv_id="2201.03545")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2201.03545", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2201.03545")
Code
The archive's official repository (facebookresearch/ConvNeXt) was not harvested; the 80 samples below come from 19 community repositories.
Syntology 80 code samples harvested from 19 repositories linked to this paper: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified. Where Syntology's instrument failed: 6 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: community (archive-listed): 80 samples from 19 repositories, 57 ran (49 with no instrument failure; 8 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 17 of its repositories that Syntology harvested for other papers:
- rwightman/pytorch-image-models, named in the paper: harvested for another paper, listed under the repository
- IMvision12/keras-vision-models, community (archive-listed): harvested for another paper, listed under the repository
- Westlake-AI/openmixup, community (archive-listed): harvested for 4 other papers, listed under the repository
- duyhominhnguyen/LVM-Med, community (archive-listed): harvested for another paper, listed under the repository
- hmichaeli/alias_free_convnets, community (archive-listed): harvested for another paper, listed under the repository
- james77777778/keras-image-models, community (archive-listed): harvested for another paper, listed under the repository
- lucidrains/denoising-diffusion-pytorch, community (archive-listed): harvested for 3 other papers, listed under the repository
- martinsbruveris/tensorflow-image-models, community (archive-listed): harvested for another paper, listed under the repository
- yaya-yns/tart, community (archive-listed): harvested for another paper, listed under the repository
- zibbini/convnext-v2_tensorflow, community (archive-listed): harvested for another paper, listed under the repository
- MindCode-4/code-3, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PASSL, community (archive-listed): harvested for another paper, listed under the repository
- keras-team/keras, community (archive-listed): harvested for another paper, listed under the repository
- leondgarse/keras_cv_attention_models, community (archive-listed): harvested for another paper, listed under the repository
- lyqcom/convnext, community (archive-listed): harvested for another paper, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmclassification, community (archive-listed): harvested for another paper, 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.
54 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
80 samples harvested: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 12 of the 80 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 19 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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 25 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.
40d3c39a403ae1f7 · report
fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24 698131638ff8d4ad · report
fixture: signature params:list/1/Param, weight_decay:float/0/float · returned list · level recorded 2026-09-24 e5a370ee6856bd8d · report
fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24 b85a6569fd4f3890 · report
fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-24 ac95eb88d9b993fd · report
b2b0744532c3b95e · report
fixture: returned ConvNeXt · level recorded 2026-09-22 ea89b2384c71ce06 · report
fixture: returned ConvNeXtBlock · level recorded 2026-09-22 b7361cb0c1592f4b · report
fixture: returned DepthwiseConv2D · level recorded 2026-09-22 census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket jax_models/models/convnext.py unverified Apache-2.0 (permissive) ·
983cc65c35c3d898 · report
a505d8b9327be637 · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22 3649cd96f92a4aa2 · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket PyTorch/models/convnext.py ran no licence file found · pointer only ·
114ebf6f5300f50a · report
fixture: returned Block · level recorded 2026-09-22 21ca7a5eca0f20a7 · report
fixture: returned ConvNeXt · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket PyTorch/models/convnext.py ran no licence file found · pointer only ·
61d5fe387e5aea75 · report
fixture: returned LayerNorm · level recorded 2026-09-22 65848fdb560a8378 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 5d3e948c34fafbe5 · report
fixture: signature norm:str/0/str, C:int/0/int, light:bool/0/bool · returned BatchNorm2d · level recorded 2026-09-24 d124421cd6cbfc19 · report
c8ac0dd572294b23 · report
fixture: returned Bottlenext · level recorded 2026-09-22 3851860b73cb71a9 · report
fixture: returned LayerNorm2d · level recorded 2026-09-22 c237d46e09539ba8 · report
fixture: returned LayerScale · level recorded 2026-09-22 62ec6c525f2f3b37 · report
fixture: returned _ResBlock · level recorded 2026-09-22 fcdf8de474c4cbd1 · report
0ff468c9fc7688e2 · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket models/convnext3d.py ran licence not identified · pointer only ·
e5136463e3d9b5d9 · report
fixture: returned Block · level recorded 2026-09-22 9a81a26d651f9883 · report
fixture: returned ConvNeXt3d · level recorded 2026-09-22 28aceeb7bc019d43 · report
fixture: returned GRN · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket models/convnext3d.py ran fingerprinted licence not identified · pointer only ·
dff029ed85c168ca · report
fixture: returned LayerNorm · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket models/convnext_dcls.py unverified MIT (permissive) ·
dd371307a76c00b0 · report
34a4f57109d0223a · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 10f409a671e88bc3 · report
fixture: returned Conv2dWrapper · level recorded 2026-09-22 fda3c94b54e0b559 · report
fixture: returned ConvNeXtBlock · level recorded 2026-09-22 d412faa4209a95a5 · report
fixture: returned LayerNorm2d · level recorded 2026-09-22 650e4fe6e5133c60 · report
fixture: returned Stem · level recorded 2026-09-22 684bcd34dc5acda1 · report
fixture: returned TransposedLN · level recorded 2026-09-22 a60bd2bbb558fe05 · report
fixture: returned TransposedLinear · level recorded 2026-09-22 b6b433072be7fbfc · report
fixture: signature tensor:Tensor/2/float · returned bool · level recorded 2026-09-22 33404a7aa263cc2d · report
dd3de6705b10dead · report
d0c0db9b61ce43ef · report
7476dcb06a6af0ae · report
37e6df5d4164c8af · report
c096f8217b69c316 · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket models/convnext.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) ·
adc5d3ca9a21de02 · report
fixture: returned Block · level recorded 2026-09-22 f4445f68e74841d0 · report
fixture: returned ConvNeXt · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket models/convnext.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) ·
c34db513de5535f1 · report
fixture: returned LayerNorm · level recorded 2026-09-22 0a9ccfaec6460f9b · report
fixture: returned ConvNeXt · level recorded 2026-09-22 cfe765a405ec911f · report
fixture: returned Downsample · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket semseg/models/backbones/convnext.py ran fingerprinted MIT (permissive) ·
80c7b022ae7942ed · report
fixture: returned LayerNorm · level recorded 2026-09-22 d3287c301a9e5d2a · report
fixture: returned Stem · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket semseg/models/backbones/convnext.py unverified MIT (permissive) ·
dd9421b72f48ad6d · report
9158c58fe9eb4b02 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 9e1c193413b20e6e · report
fixture: returned ConvNeXtStage · level recorded 2026-09-22 baad12607c91ab0b · report
fixture: returned Mlp · level recorded 2026-09-22 a5e8dd4f5b4997a9 · report
fixture: signature key:ArrayImpl/1/int, shape:tuple/1/int, dtype:callable/0/?, constant:float/0/float · returned ArrayImpl · level recorded 2026-09-22 af08f1375360cd95 · report
fixture: signature key:ArrayImpl/1/int, shape:tuple/1/int, dtype:callable/0/?, std:float/0/float · returned ArrayImpl · level recorded 2026-09-22 census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket audax/models/convnext.py ran; the contract check could not run (RAISES) fingerprinted BSD-2-Clause (permissive) ·
743bf392200483a3 · report
fixture: signature x:ArrayImpl/4/float, rng:ArrayImpl/1/int, drop_prob:float/0/float · returned ArrayImpl · level recorded 2026-09-22 414ef464242b98e7 · report
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket audax/models/convnext.py unverified BSD-2-Clause (permissive) ·
0c184b9cfad87e20 · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket models/convnext.py ran · metamorphic tier: invariant MIT (permissive) ·
c7a4a3371425c3ed · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket light_cnns/Transformer/ConvNeXt.py ran MIT (permissive) ·
0bf3c80a4d223969 · report
fixture: returned Block · level recorded 2026-09-22 305d76901873eee2 · report
fixture: returned ConvNeXt · level recorded 2026-09-22 census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket light_cnns/Transformer/ConvNeXt.py ran fingerprinted MIT (permissive) ·
6255e860ca403ee6 · report
fixture: returned DropPath · level recorded 2026-09-22 89c908636a8e0602 · report
fixture: returned CNBlock · level recorded 2026-09-22 717211755e50eb05 · report
fixture: returned CNBlockConfig · level recorded 2026-09-22 2748b257d8ff4d3d · report
fixture: returned ConvNormActivation · level recorded 2026-09-22 a3e629aa4dc78889 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 65b8909854f686af · report
fixture: returned Permute · level recorded 2026-09-22 8e01c115449d22b7 · report
fixture: returned StochasticDepth · level recorded 2026-09-22 793c01e18742fca2 · report
fixture: signature x:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-22 a796360490702186 · report
fixture: signature input:Tensor/4/float, p:float/0/float, mode:str/0/str, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 9a10ee44c3d37cd1 · report
1b8e89a263fe7ec2 · report
59d110860cf7a38a · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket towhee/models/convnext/convnext.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) ·
2dd46bec59a83b7b · report
fixture: returned Block · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket towhee/models/convnext/convnext.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) ·
a0d926a08b9cf439 · report
fixture: returned LayerNorm · level recorded 2026-09-22 6670f25cb82fb974 · 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.
18 assemblies on this paper: 18 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
18 sibling assemblies for ConvNeXt (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 18 sibling assemblies; the other 6 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 3 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) · 1 unverified. The assembly has not been run end-to-end.
one of 18 siblings
- Unet3plus entry · level 0 · unverified ·
df5508fa2861f149 - double_conv helper · level 1 · ran · our draft was wrong ·
a505d8b9327be637 - single_conv helper · level 1 · ran · our draft was wrong ·
3649cd96f92a4aa2
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 7 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 0 · unverified ·
6670f25cb82fb974 - Block model · level 1 · ran ·
2dd46bec59a83b7b - LayerNorm helper · level 1 · ran ·
a0d926a08b9cf439 - trunc_normal_ helper · level 1 · ran; the contract check could not run ·
f3e47c6e3250d13b - DropPath helper · level 1 · ran ·
8f059bf3db11537b - drop_path helper · level 1 · ran; the contract check could not run ·
39eace7e2822504f - _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run ·
607038475fdc388b
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 3 bricks; individually on a fixture: 3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 4 bricks; individually on a fixture: 3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 1 · ran ·
b2b0744532c3b95e - ConvNeXtBlock model · level 1 · ran ·
ea89b2384c71ce06 - DepthwiseConv2D model · level 1 · ran ·
b7361cb0c1592f4b - DropPath helper · level 0 · unverified ·
983cc65c35c3d898
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 6 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 0 · unverified ·
fcdf8de474c4cbd1 - Bottlenext model · level 1 · ran ·
c8ac0dd572294b23 - LayerNorm2d helper · level 1 · ran ·
3851860b73cb71a9 - conv_sequence helper · level 0 · unverified ·
0ff468c9fc7688e2 - LayerScale helper · level 1 · ran ·
c237d46e09539ba8 - _ResBlock helper · level 1 · ran ·
62ec6c525f2f3b37
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 3 bricks; individually on a fixture: 3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 11 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 0 · unverified ·
33404a7aa263cc2d - ConvNeXtStage model · level 0 · unverified ·
dd3de6705b10dead - LayerNorm2d helper · level 1 · ran ·
d412faa4209a95a5 - Stem model · level 1 · ran ·
650e4fe6e5133c60 - TransposedLN helper · level 1 · ran ·
684bcd34dc5acda1 - _init_weights helper · level 0 · unverified ·
7476dcb06a6af0ae - Conv2dWrapper helper · level 1 · ran ·
10f409a671e88bc3 - ConvNeXtBlock model · level 1 · ran ·
fda3c94b54e0b559 - S4DownSample model · level 0 · unverified ·
d0c0db9b61ce43ef - _is_contiguous helper · level 1 · ran · our draft was wrong ·
b6b433072be7fbfc - TransposedLinear helper · level 1 · ran ·
a60bd2bbb558fe05
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 8 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) · 3 unverified. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 0 · unverified ·
af5901026319567f - ConvNeXtStage model · level 1 · ran ·
9e1c193413b20e6e - ConvNeXtBlock model · level 0 · unverified ·
414ef464242b98e7 - DropPath helper · level 0 · unverified ·
0c184b9cfad87e20 - Mlp helper · level 1 · ran ·
baad12607c91ab0b - constant_init helper · level 1 · ran · our draft was wrong ·
a5e8dd4f5b4997a9 - drop_path helper · level 1 · ran; the contract check could not run (RAISES) ·
743bf392200483a3 - convnext_truncated_init helper · level 1 · ran · our draft was wrong ·
af08f1375360cd95
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
- ConvNeXt entry · level 1 · ran ·
0a9ccfaec6460f9b - Block model · level 0 · unverified ·
dd9421b72f48ad6d - Downsample model · level 1 · ran ·
cfe765a405ec911f - LayerNorm helper · level 1 · ran ·
80c7b022ae7942ed - Stem model · level 1 · ran ·
d3287c301a9e5d2a
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 18 siblings
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 5 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 18 siblings
harvested Assembly for ConvNeXt (graph method: ConvNeXt). 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 18 siblings
- convnext_1 entry · level 1 · ran ·
9158c58fe9eb4b02
- ConvNeXt · 9aecb772459ffb6e · 11 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- ConvNeXt · a1a28e270a2ef9b3 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- ConvNeXt_dcls · a2bef7b9b987cf0c · 3 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) · 2 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- ConvNeXt · c9e98de4e04bd3d4 · 3 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- InvBottleneck · f4bbfa1969a563cc · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 · assemblies[16] in the JSON twin
- SepConv · ffbfceb53ae91dea · 3 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[17] 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="2201.03545") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Classification | InDL | ConvNext | Average Recall | 93.47% | #1 of 9 | Archive leaderboard | report |
| Domain Generalization | ImageNet-A | ConvNeXt-XL (Im21k, 384) | Top-1 accuracy % | 69.3 | #10 of 39 | Archive leaderboard | report |
| Domain Generalization | ImageNet-C | ConvNeXt-XL (Im21k) (augmentation overlap with ImageNet-C) | Number of params | 350M | #12 of 47 | Archive leaderboard | report |
| Domain Generalization | ImageNet-C | ConvNeXt-XL (Im21k) (augmentation overlap with ImageNet-C) | mean Corruption Error (mCE) | 38.8 | #12 of 47 | Archive leaderboard | report |
| Domain Generalization | ImageNet-R | ConvNeXt-XL (Im21k, 384) | Top-1 Error Rate | 31.8 | #8 of 39 | Archive leaderboard | report |
| Domain Generalization | ImageNet-Sketch | ConvNeXt-XL (Im21k, 384) | Top-1 accuracy | 55.0 | #4 of 20 | Archive leaderboard | report |
| Domain Generalization | VizWiz-Classification | ConvNeXt-B | Accuracy - All Images | 53.5 | #2 of 90 | Archive leaderboard | report |
| Domain Generalization | VizWiz-Classification | ConvNeXt-B | Accuracy - Clean Images | 56 | #2 of 90 | Archive leaderboard | report |
| Domain Generalization | VizWiz-Classification | ConvNeXt-B | Accuracy - Corrupted Images | 46.9 | #2 of 90 | Archive leaderboard | report |
| Image Classification | ImageNet | Adlik-ViT-SG+Swin_large+Convnext_xlarge(384) | Number of params | 1827M | #51 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Adlik-ViT-SG+Swin_large+Convnext_xlarge(384) | Top 1 Accuracy | 88.36% | #51 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-XL (ImageNet-22k) | GFLOPs | 179 | #72 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-XL (ImageNet-22k) | Number of params | 350M | #72 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-XL (ImageNet-22k) | Top 1 Accuracy | 87.8% | #72 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-L (384 res) | GFLOPs | 101 | #226 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-L (384 res) | Number of params | 198M | #226 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-L (384 res) | Top 1 Accuracy | 85.5% | #226 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-T | GFLOPs | 4.5 | #576 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-T | Number of params | 29M | #576 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ConvNeXt-T | Top 1 Accuracy | 82.1% | #576 of 1060 | Archive leaderboard | report |
| Object Detection | COCO-O | ConvNeXt-XL (Cascade Mask R-CNN) | Average mAP | 37.5 | #7 of 45 | Archive leaderboard | report |
| Object Detection | COCO-O | ConvNeXt-XL (Cascade Mask R-CNN) | Effective Robustness | 12.68 | #7 of 45 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-XL++ | GFLOPs (512 x 512) | 3335 | #69 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-XL++ | Params (M) | 391 | #69 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-XL++ | Validation mIoU | 54 | #69 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-L++ | GFLOPs (512 x 512) | 2458 | #74 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-L++ | Params (M) | 235 | #74 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-L++ | Validation mIoU | 53.7 | #74 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B++ | GFLOPs (512 x 512) | 1828 | #83 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B++ | Params (M) | 122 | #83 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B++ | Validation mIoU | 53.1 | #83 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B | GFLOPs (512 x 512) | 1170 | #123 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B | Params (M) | 122 | #123 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-B | Validation mIoU | 49.9 | #123 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-S | GFLOPs (512 x 512) | 1027 | #129 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-S | Params (M) | 82 | #129 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-S | Validation mIoU | 49.6 | #129 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-T | GFLOPs (512 x 512) | 939 | #172 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-T | Params (M) | 60 | #172 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | ConvNeXt-T | Validation mIoU | 46.7 | #172 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ImageNet-S | ConvNext-Tiny (P4, 224x224, SUP) | mIoU (test) | 48.8 | #11 of 20 | Archive leaderboard | report |
| Semantic Segmentation | ImageNet-S | ConvNext-Tiny (P4, 224x224, SUP) | mIoU (val) | 48.7 | #11 of 20 | 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
Introduced by this paper: ConvNeXt
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