Papers › ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

2 Jan 2023CVPR 2023 1arXiv:2301.00808archive 2025-07-28

Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

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 5 repositories linked to this paper: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 12 samples from 4 repositories, 11 ran (8 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.

No sample is linked to this paper from 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

17 repositories listed; official and paper-mentioned ones first.

facebookresearch/convnext-v2 officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
rwightman/pytorch-image-models mentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
IMvision12/keras-vision-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
Jacky-Android/convnext-v2-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 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) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
chenller/mmseg-extension mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions (arXiv:2211.05778; that paper's own run record: 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) · 2 unverified), BiFormer: Vision Transformer with Bi-Level Routing Attention (arXiv:2303.08810; that paper's own run record: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), TransNeXt: Robust Foveal Visual Perception for Vision Transformers (arXiv:2311.17132; that paper's own run record: 5 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; 3 where Syntology's instrument failed) · 0 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
vishalned/MMEarth-train mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
zibbini/convnext-v2_tensorflow mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
Mind23-2/MindCode-22 mindsporeSyntology: not harvested report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 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); nothing checks that they implement this paper's method. report
MindSpore-paper-code-3/code7 mindsporeSyntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 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) · 6 unverified); nothing checks that they implement this paper's method. report
lyqcom/convnext mindsporeApache-2.0Syntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
pwc-1/Paper-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 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); nothing checks that they implement this paper's method. report
gitlab.com/birder/birder pytorchSyntology: not harvested 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.

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

14 samples harvested: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 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.

3ran · our draft was wrong
10ran
1unverified

Licence: 12 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 5 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.

facebookresearch/convnext-v2 official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/convnextv2.py ran · metamorphic tier: invariant licence not identified · pointer only · 24e783957539d177 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ConvNeXtV2 models/convnextv2.py ran · metamorphic tier: invariant licence not identified · pointer only · 420fed3739fee70b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Jacky-Android/convnext-v2-pytorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model.py ran no licence file found · pointer only · f3c65efbbcd4b2a2 · report fixture: returned Block · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model.py ran fingerprinted no licence file found · pointer only · 649912d2ea60c644 · report fixture: returned LayerNorm · level recorded 2026-09-22
ConvNeXtV2 model.py unverified no licence file found · pointer only · 4b87ad6572b3686e · report
vishalned/MMEarth-train community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/convnextv2.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2c6904dfd0e3ee2a · report fixture: returned Block · level recorded 2026-09-22
ConvNeXtV2 models/convnextv2.py ran · metamorphic tier: deterministic licence not identified · pointer only · d8c0f250ae1c4733 · report fixture: returned ConvNeXtV2 · level recorded 2026-09-22
GRN models/convnextv2.py ran · metamorphic tier: invariant licence not identified · pointer only · 4035f346a2e3d70e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/convnextv2.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2f8121a6bb6bf49c · report fixture: returned LayerNorm · level recorded 2026-09-22
zibbini/convnext-v2_tensorflow community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
convnext_pt/convnextv2.py ran MIT (permissive) · af25ab15eb29c44b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ConvNeXtV2 convnext_pt/convnextv2.py ran MIT (permissive) · 0b701ad2d565c3a4 · report fixture: returned ConvNeXtV2 · level recorded 2026-09-22
lyqcom/convnext community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
arg_to_varname in 10 papers src/configs/parser.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 177a4abf40724f6e · report fixture: signature st:str/0/str · returned str · level recorded 2026-09-25
argv_to_vars in 10 papers src/configs/parser.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ffc9d7cced6f71fb · report fixture: signature argv:list/1/str · returned list · level recorded 2026-09-25
trim_preceding_hyphens in 10 papers src/configs/parser.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a99f170ebd682af5 · report fixture: signature st:str/0/str · returned str · level recorded 2026-09-25

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.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for ConvNeXt V2 (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for ConvNeXt V2 (graph method: ConvNeXt V2). 4 bricks; individually on a fixture: 4 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ConvNeXtV2 entry · level 1 · ran · d8c0f250ae1c4733
  2. Block model · level 1 · ran · 2c6904dfd0e3ee2a
  3. LayerNorm helper · level 1 · ran · 2f8121a6bb6bf49c
  4. GRN helper · level 1 · ran · 4035f346a2e3d70e

harvested Assembly for ConvNeXt V2 (graph method: ConvNeXt V2). 4 bricks; individually on a fixture: 4 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ConvNeXtV2 entry · level 1 · ran · 0b701ad2d565c3a4
  2. Block helper · level 1 · ran · af25ab15eb29c44b
  3. LayerNorm helper · level 1 · ran · 2f8121a6bb6bf49c
  4. GRN helper · level 1 · ran · 1ab5d1761e67dbec

harvested Assembly for ConvNeXt V2 (graph method: ConvNeXt V2). 6 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) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ConvNeXtV2 entry · level 0 · unverified · 4b87ad6572b3686e
  2. Block model · level 1 · ran · f3c65efbbcd4b2a2
  3. LayerNorm model · level 1 · ran · 649912d2ea60c644
  4. DropPath model · level 1 · ran · 75f5c156267fccbd
  5. GRN model · level 1 · ran · 1ab5d1761e67dbec
  6. drop_path helper · level 1 · ran; the contract check could not run · 3ac6b7d76e8e3584

harvested Assembly for ConvNeXt V2 (graph method: ConvNeXt V2). 4 bricks; individually on a fixture: 4 ran (of which 2 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. The assembly has not been run end-to-end.

one of 4 siblings

  1. ConvNeXtV2 entry · level 1 · ran · 420fed3739fee70b
  2. Block helper · level 1 · ran · 24e783957539d177
  3. LayerNorm helper · level 1 · ran · 2f8121a6bb6bf49c
  4. GRN helper · level 1 · ran · 1ab5d1761e67dbec

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="2301.00808") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Object DetectionRepresentation LearningSelf-Supervised LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K ConvNeXt V2-H (FCMAE) Validation mIoU 55 #51 of 235 Archive leaderboard report
Semantic Segmentation ADE20K Swin V2-H Validation mIoU 54.2 #66 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ConvNeXt V2-L Validation mIoU 53.7 #76 of 235 Archive leaderboard report
Semantic Segmentation ADE20K Swin-L Validation mIoU 53.5 #81 of 235 Archive leaderboard report
Semantic Segmentation ADE20K Swin-B Validation mIoU 52.8 #87 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ConvNeXt V2-B Validation mIoU 52.1 #89 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ConvNeXt V2-L (Supervised) Validation mIoU 51.6 #94 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ConvNeXt V1-L Validation mIoU 50.5 #112 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ConvNeXt V1-B Validation mIoU 49.9 #125 of 235 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

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