SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.00808 · CVPR · 2023

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

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

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.00808.json · badge: /api/ran/2301.00808.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
vishalned/MMEarth-train community
Papers with Code archive
4 ran · 0 no recorded run
lyqcom/convnext community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
Jacky-Android/convnext-v2-pytorch community
Papers with Code archive
2 ran · 1 no recorded run
zibbini/convnext-v2_tensorflow community
Papers with Code archive
2 ran · 0 no recorded run
facebookresearch/convnext-v2 marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
vishalned/MMEarth-train/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("2c6904dfd0e3ee2a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vishalned/MMEarth-train (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Block Ran
ran on a synthesized input
zibbini/convnext-v2_tensorflow/convnext_pt/convnextv2.py
code served (permissive licence) · get_code("af25ab15eb29c44b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.nn.functional as F
from timm.models.layers import trunc_normal_, DropPath

class GRN(nn.Module):
    """ GRN (Global Response Normalization) layer
    """

    def __init__(self, dim):
        super().__init__()
        self.gamma = nn.Parameter(torch.zeros(1, 1, 1, dim))
        self.beta = nn.Parameter(torch.zeros(1, 1, 1, dim))

    def forward(self, x):
        Gx = torch.norm(x, p=2, dim=(1, 2), keepdim=True)
        Nx = Gx / (Gx.mean(dim=-1, keepdim=True) + 1e-06)
        return self.gamma * (x * Nx) + self.beta + x

class LayerNorm(nn.Module):
    """ LayerNorm that supports two data formats: channels_last (default) or channels_first. 
    The ordering of the dimensions in the inputs. channels_last corresponds to inputs with 
    shape (batch_size, height, width, channels) while channels_first corresponds to inputs 
    with shape (batch_size, channels, height, width).
    """

    def __init__(self, normalized_shape, eps=1e-06, data_format='channels_last'):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ['channels_last', 'channels_first']:
            raise NotImplementedError
        self.normalized_shape = (normalized_shape,)

    def forward(self, x):
        if self.data_format == 'channels_last':
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == 'channels_first':
            u = x.mean(1, keepdim=True)
            s = (x - u).pow(2).mean(1, keepdim=True)
            x = (x - u) / torch.sqrt(s + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x

class Block(nn.Module):
    """ ConvNeXtV2 Block.
    
    Args:
        dim (int): Number of input channels.
        drop_path (float): Stochastic depth rate. Default: 0.0
    """

    def __init__(self, dim, drop_path=0.0):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)
        self.norm = LayerNorm(dim, eps=1e-06)
        self.pwconv1 = nn.Linear(dim, 4 * dim)
        self.act = nn.GELU()
        self.grn = GRN(4 * dim)
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.grn(x)
        x = self.pwconv2(x)
        x = x.permute(0, 3, 1, 2)
        x = input + self.drop_path(x)
        return x


INIT_ARGS = {
    'dim': 4,
    'drop_path': 0.0,
}

ARGS = {
    'x': torch.randn(2, 4, 3, 5),
}

if __name__ == '__main__':
    block = Block(**INIT_ARGS)
    output = block(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print("Block executed successfully!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Block Ran
ran on a synthesized input · constructed an object; no result was computed
Jacky-Android/convnext-v2-pytorch/model.py
pointer only (licence: NONE) · get_code("f3c65efbbcd4b2a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jacky-Android/convnext-v2-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Block Ran
ran on a synthesized input
facebookresearch/convnext-v2/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("24e783957539d177")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/convnext-v2 (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvNeXtV2 Ran
ran on a synthesized input · constructed an object; no result was computed
vishalned/MMEarth-train/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("d8c0f250ae1c4733")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vishalned/MMEarth-train (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvNeXtV2 Ran
ran on a synthesized input · constructed an object; no result was computed
zibbini/convnext-v2_tensorflow/convnext_pt/convnextv2.py
code served (permissive licence) · get_code("0b701ad2d565c3a4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, ConvNeXtV2: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_chans': 3,
    'num_classes': 10,
    'depths': [2, 2, 2, 2],
    'dims': [32, 64, 128, 256],
    'drop_path_rate': 0.1,
    'head_init_scale': 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ConvNeXtV2 — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConvNeXtV2 output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ConvNeXtV2 Ran
ran on a synthesized input
facebookresearch/convnext-v2/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("420fed3739fee70b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/convnext-v2 (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GRN Ran
ran on a synthesized input
vishalned/MMEarth-train/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("4035f346a2e3d70e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vishalned/MMEarth-train (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
vishalned/MMEarth-train/models/convnextv2.py
pointer only (licence: NOASSERTION) · get_code("2f8121a6bb6bf49c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vishalned/MMEarth-train (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
Jacky-Android/convnext-v2-pytorch/model.py
pointer only (licence: NONE) · get_code("649912d2ea60c644")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jacky-Android/convnext-v2-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

arg_to_varname Ran
ran; our contract draft was wrong, not the code
lyqcom/convnext/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("177a4abf40724f6e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

argv_to_vars Ran
ran; our contract draft was wrong, not the code
lyqcom/convnext/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("ffc9d7cced6f71fb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

trim_preceding_hyphens Ran
ran; our contract draft was wrong, not the code
lyqcom/convnext/src/configs/parser.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Seongyeol-kim/FedWSQ, is pointer only (licence: NONE) · get_code("a99f170ebd682af5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Seongyeol-kim/FedWSQ, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvNeXtV2 Not yet run
unverified (harvested, no recorded run)
Jacky-Android/convnext-v2-pytorch/model.py
pointer only (licence: NONE) · get_code("4b87ad6572b3686e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jacky-Android/convnext-v2-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
LayerNorm
brick of this paper's assembly: helper
14 other papers
2 dated earlier, 12 later · 9 only as an assembly brick
2110.02178 (2021-10)
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
2201.03545 (2022-01)
A ConvNet for the 2020s
2303.15446 (2023-03)
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
and 11 more not named here
arg_to_varname 9 other papers
7 dated earlier, 2 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 6 more not named here
trim_preceding_hyphens 9 other papers
7 dated earlier, 2 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 6 more not named here
argv_to_vars 8 other papers
6 dated earlier, 2 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2104.00298 (2021-04)
EfficientNetV2: Smaller Models and Faster Training
and 5 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 [33], 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) [14]. 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 3.7Mparameter Atto model with 76.7% top-1 accuracy on Im-ageNet, to a 650M Huge model that achieves a state-of-theart 88.9% accuracy using only public training data.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.00808")
get_code_for_paper("2301.00808")
have("2301.00808")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.00808.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.00808.svg)](https://syntology.ai/paper/2301.00808)

Connect an agent — have() is free.