Papers › Masked Autoencoders Are Scalable Vision Learners

Masked Autoencoders Are Scalable Vision Learners

11 Nov 2021CVPR 2022 1arXiv:2111.06377archive 2025-07-28

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. First, we develop an asymmetric encoder-decoder architecture, with an encoder that operates only on the visible subset of patches (without mask tokens), along with a lightweight decoder that reconstructs the original image from the latent representation and mask tokens. Second, we find that masking a high proportion of the input image, e.g., 75%, yields a nontrivial and meaningful self-supervisory task. Coupling these two designs enables us to train large models efficiently and effectively: we accelerate training (by 3x or more) and improve accuracy. Our scalable approach allows for learning high-capacity models that generalize well: e.g., a vanilla ViT-Huge model achieves the best accuracy (87.8%) among methods that use only ImageNet-1K data. Transfer performance in downstream tasks outperforms supervised pre-training and shows promising scaling behavior.

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

No sample from the archive's official repository (facebookresearch/mae) is linked to this paper; the 136 samples below come from 30 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from facebookresearch/mae for another paper.

facebookresearch/mae: Syntology's graph links these samples to Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra (arXiv:2605.24770; 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) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 137 code samples: 136 from 30 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 137: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 12 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 136 samples from 30 repositories, 85 ran (67 with no instrument failure; 18 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 13 of its repositories that Syntology harvested for other papers:

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. 1 of the 86 samples that ran has no recorded date.

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

facebookresearch/mae officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra (arXiv:2605.24770; 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) · 0 unverified); nothing checks that they implement this paper's method. report
0jason000/mae_vit mentioned on GitHubmindsporeApache-2.0Syntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
2020132075/conmae mentioned on GitHubpytorchSyntology: not harvested report
BUPT-PRIV/MAE-priv mentioned on GitHubpytorchSyntology: 8 samples, 3 ran (0 instrument-failed) · 5 unverified report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: 12 samples, 7 ran (1 instrument-failed) · 5 unverified report
FlyEgle/MAE-pytorch mentioned on GitHubpytorchSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified report
IcarusWizard/MAE mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (1 instrument-failed) · 0 unverified report
Nullius-2020/MAE-Paddle mentioned on GitHubpaddleMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
SnailDev/github-hot-hub mentioned on GitHubpytorchMITSyntology: not harvested report
Ugenteraan/Masked-AutoEncoder-PyTorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. 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
aHapBean/PCP-MAE mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative... (arXiv:2302.02318; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 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
alicebizeul/pmae mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
ariG23498/mae-scalable-vision-learners mentioned on GitHubtfMITSyntology: not harvested report
bwconrad/masked-autoencoder mentioned on GitHubpytorchSyntology: 10 samples, 1 ran (0 instrument-failed) · 9 unverified report
dispink/xpt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. report
dominickrei/limited-data-vits mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
dravenww/curated-article mentioned on GitHubtfSyntology: not harvested report
facebookresearch/hiera mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles (arXiv:2306.00989; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
facebookresearch/multimodal mentioned on GitHubpytorchSyntology: 12 samples, 11 ran (5 instrument-failed) · 1 unverified report
facebookresearch/vip-mae mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
guilk/vlc mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
hkbu-vscomputing/2022_mm_dmae-mocap mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
innat/VideoMAE mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video... (arXiv:2203.12602; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
isaaccorley/hydro-foundation-model mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
islamosmanubc/MedMAE mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
keytoyze/visionts mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
kit-mrt/masked-fusion-360 mentioned on GitHubpytorchSyntology: not harvested report
leaplabthu/efficienttrain mentioned on GitHubpytorchMITSyntology: not harvested report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Momentum Contrast for Unsupervised Visual Representation Learning (arXiv:1911.05722; that paper's own run record: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified), A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified), Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (arXiv:2006.09882; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified) and 8 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
liujiyuan13/MAE-code mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
lonnyzhang423/github-hot-hub mentioned on GitHubpytorchMITSyntology: not harvested report
mx-mark/videotransformer-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nasa-impact/hls-foundation-os mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
oneflow-inc/libai mentioned on GitHubApache-2.0Syntology: not harvested report
open-mmlab/mmselfsup mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling (arXiv:2303.02416; that paper's own run record: 3 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pengzhiliang/MAE-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
qiaopTDUN/mae-repo mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
virajprabhu/pacmac mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
wangsr126/mae-lite mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
wangyz1608/knowledge-distillation-via-nd mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Knowledge Distillation via Regularizing Feature Norm and Direction (arXiv:2305.17007; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
xplip/pixel mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Language Modelling with Pixels (arXiv:2207.06991; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yangsun22/tc-moa mentioned on GitHubpytorchSyntology: 18 samples, 12 ran (5 instrument-failed) · 6 unverified report
yifanzhang-pro/m-mae mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
zhangq327/u-mae mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders (arXiv:2210.08344; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zinengtang/tvlt mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
2023-MindSpore-1/ms-code-206 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code12 mindsporeSyntology: not harvested report
Asthestarsfalll/MAE-MegEngine pytorchSyntology: not harvested report
PatrickHua/SimpleMAE pytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
alibaba/EasyCV pytorchSyntology: 2 samples, 0 ran · 2 unverified report
flytocc/mae-paddle paddleNOASSERTIONSyntology: not harvested report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
three0-s/MAE-keras tfSyntology: not harvested report
yangyucheng000/MAE-2 mindsporeSyntology: not harvested report
yangyucheng000/mae mindsporeApache-2.0Syntology: 9 samples, 9 ran (1 instrument-failed) · 0 unverified report
yongyupei/papers_with_examps mindsporeApache-2.0Syntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified 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

137 samples harvested: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 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.

8ran · honoured contract
6ran · our draft was wrong
12ran; the contract check could not run
60ran
51unverified

Licence: 78 of the 137 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 30 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. 1 sample is listed last, in a group without a repository. “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 11 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.

0jason000/mae_vit community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
float_parameter in 36 papers src/transforms.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 40d3c39a403ae1f7 · report fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24
init_group_params in 7 papers src/optim.py ran Apache-2.0 (permissive) · 698131638ff8d4ad · report fixture: signature params:list/1/Param, weight_decay:float/0/float · returned list · level recorded 2026-09-24
int_parameter in 35 papers src/transforms.py ran fingerprinted Apache-2.0 (permissive) · e5a370ee6856bd8d · report fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24
is_model in 24 papers src/model.py ran Apache-2.0 (permissive) · b85a6569fd4f3890 · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-24
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
src/mae_vit.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 12035a2f77d8016c · report
get_2d_sincos_pos_embed in 170 papers src/mae_vit.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 3185afc3e87293ed · report
get_2d_sincos_pos_embed_from_grid in 140 papers src/mae_vit.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · f10004e059714d42 · report
model_entrypoint in 6 papers src/model.py unverified Apache-2.0 (permissive) · ac95eb88d9b993fd · report
BUPT-PRIV/MAE-priv community (archive-listed) 8 samples, 3 ran (0 instrument-failed) · 5 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
mae/modeling_pretrain.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 762514af1d1eeb94 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
mae/modeling_pretrain.py ran · metamorphic tier: invariant licence not identified · pointer only · 19e9a6ad7bef0ec3 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
build_2d_sincos_position_embedding mae/modeling_pretrain.py ran · honoured contract licence not identified · pointer only · 3ee2c04c92f6e311 · report fixture: signature h:int/0/int, w:int/0/int, embed_dim:int/0/int, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
PretrainVisionTransformer in 6 papers mae/modeling_pretrain.py unverified licence not identified · pointer only · 691ae52245b4ee13 · report
PretrainVisionTransformerDecoder mae/modeling_pretrain.py unverified licence not identified · pointer only · 117d7c1a13a2dcc2 · report
PretrainVisionTransformerEncoder in 5 papers mae/modeling_pretrain.py unverified licence not identified · pointer only · e561f7d0bb64a05e · report
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
mae/modeling_pretrain.py unverified licence not identified · pointer only · faee721aebff20d6 · report
DarshanDeshpande/jax-models community (archive-listed) 12 samples, 7 ran (1 instrument-failed) · 5 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
jax_models/models/masked_autoencoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2caebdfa70d265d1 · report fixture: returned Attention · level recorded 2026-09-22
DepthwiseConv2D in 8 papers jax_models/models/masked_autoencoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1eb614b14acb62c8 · report fixture: returned DepthwiseConv2D · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
jax_models/models/masked_autoencoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a84a5b2f271cf15c · report fixture: returned DropPath · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
jax_models/models/masked_autoencoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8c15bb7018339540 · report fixture: returned PatchEmbed · level recorded 2026-09-22
TransformerMLP in 5 papers jax_models/models/masked_autoencoder.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d250b23f4ed3fd00 · report fixture: returned TransformerMLP · level recorded 2026-09-22
sincosemb1d jax_models/models/masked_autoencoder.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · ba4526d5e3418ddb · report fixture: signature emb_dim:int/0/int, pos:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-22
sincosposemb jax_models/models/masked_autoencoder.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 3b6e902cfca4fc8a · report fixture: signature emb_dim:int/0/int, grid_size:int/0/int · returned ArrayImpl · level recorded 2026-09-22
Decoder in 210 papers jax_models/models/masked_autoencoder.py unverified Apache-2.0 (permissive) · b892a94c4303b6e7 · report
Encoder in 278 papers jax_models/models/masked_autoencoder.py unverified Apache-2.0 (permissive) · 9d6e5fd05d104462 · report
Mask in 10 papers jax_models/models/masked_autoencoder.py unverified Apache-2.0 (permissive) · 9ded34638fb55197 · report
MaskedAutoencoderViT in 14 papers jax_models/models/masked_autoencoder.py unverified Apache-2.0 (permissive) · db65696502e25065 · report
FlyEgle/MAE-pytorch community (archive-listed) 11 samples, 7 ran (2 instrument-failed) · 4 unverified
MaskEmbeeding model/Transformers/VIT/mae.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 7168cb5bb5682694 · report fixture: signature token_emb:Tensor/3/float, mask_ratio:float/0/float · returned tuple · level recorded 2026-09-22
MaskTransLayerNorm model/Transformers/VIT/mae.py ran no licence file found · pointer only · 214b8df5981d09c7 · report fixture: returned MaskTransLayerNorm · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
model/Transformers/VIT/mae.py ran no licence file found · pointer only · fef9f7a5f84c313e · report fixture: returned PatchEmbed · level recorded 2026-09-22
PositionEmbed model/Transformers/VIT/mae.py ran no licence file found · pointer only · 5c8ef9e803d379dd · report fixture: returned PositionEmbed · level recorded 2026-09-22
ShuffleIndex model/Transformers/VIT/mae.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 757bdfb554d8bc1c · report fixture: signature index:list/1/int, sample_ratio:float/0/float · returned tuple · level recorded 2026-09-22
UnMaskEmbeeding model/Transformers/VIT/mae.py ran no licence file found · pointer only · 315d68728f9a0983 · report fixture: returned UnMaskEmbeeding · level recorded 2026-09-22
to_2tuple in 25 papers model/Transformers/VIT/mae.py ran · honoured contract fingerprinted no licence file found · pointer only · 5a717e76320e4864 · report fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22
MAEVisionTransformers model/Transformers/VIT/mae.py unverified no licence file found · pointer only · a4895ce8a87f02d2 · report
Mlp in 102 papers model/Transformers/VIT/mae.py unverified no licence file found · pointer only · e8f3808093706645 · report
VisionTransformer in 53 papers model/Transformers/VIT/mae.py unverified no licence file found · pointer only · 19ec788aecbdfc22 · report
IcarusWizard/MAE community (archive-listed) 6 samples, 6 ran (1 instrument-failed) · 0 unverified
MAE_Decoder model.py ran MIT (permissive) · 171529a77f4acb67 · report fixture: returned MAE_Decoder · level recorded 2026-09-22
MAE_Encoder model.py ran MIT (permissive) · 5a460b0d402e326f · report fixture: returned MAE_Encoder · level recorded 2026-09-22
MAE_ViT model.py ran MIT (permissive) · 7df7897de7c5b685 · report fixture: returned MAE_ViT · level recorded 2026-09-22
PatchShuffle model.py ran fingerprinted MIT (permissive) · a9838138fb194e4e · report fixture: returned PatchShuffle · level recorded 2026-09-22
random_indexes model.py ran · honoured contract MIT (permissive) · cc4c605a1dd69746 · report fixture: signature size:int/0/int · returned tuple · level recorded 2026-09-22
take_indexes model.py ran · our draft was wrong MIT (permissive) · 0dee20694ea4b3ee · report fixture: signature sequences:Tensor/3/float, indexes:Tensor/2/int · returned Tensor · level recorded 2026-09-22
Nullius-2020/MAE-Paddle community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
update_config in 54 papers config.py ran MIT (permissive) · 057888637b943025 · report fixture: signature config:Config/0/?, args:Namespace/0/? · returned Config · level recorded 2026-09-24
get_config in 203 papers config.py unverified MIT (permissive) · 160fd4002bd2e51b · report
alicebizeul/pmae community (archive-listed) 1 sample, 0 ran · 1 unverified
ViTMAEForPreTraining src/model/vit_mae.py unverified no licence file found · pointer only · 3251c65d1624eba1 · report
bwconrad/masked-autoencoder community (archive-listed) 10 samples, 1 ran (0 instrument-failed) · 9 unverified
LinearDecoder src/model.py ran no licence file found · pointer only · 8c2a5e9356370f98 · report fixture: returned LinearDecoder · level recorded 2026-09-22
MaskedAutoencoderModel src/model.py unverified no licence file found · pointer only · 8e71ab74b3539260 · report
VisionTransformerDecoder src/model.py unverified no licence file found · pointer only · 65d6b4d0f5c0932c · report
VisionTransformerMAE src/model.py unverified no licence file found · pointer only · 7b0c5df25df03a0f · report
build_encoder in 17 papers src/model.py unverified no licence file found · pointer only · e18efe0723eb391d · report
vit_base_patch16 src/model.py unverified no licence file found · pointer only · e74f91045366913e · report
vit_huge_patch14 src/model.py unverified no licence file found · pointer only · 16f4365f89fc1383 · report
vit_large_patch16 src/model.py unverified no licence file found · pointer only · 404d47a8e8939ea1 · report
vit_small_patch16 src/model.py unverified no licence file found · pointer only · bd06f7ac78d039d0 · report
vit_tiny_patch16 src/model.py unverified no licence file found · pointer only · d1699368ffaa6920 · report
dominickrei/limited-data-vits community (archive-listed) 1 sample, 0 ran · 1 unverified
MaskedAutoencoderViT in 14 papers models_mae.py unverified no licence file found · pointer only · eb084414ba03cd0e · report
facebookresearch/multimodal community (archive-listed) 12 samples, 11 ran (5 instrument-failed) · 1 unverified
DecoderEmbeddings torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · 50340b2a447969fb · report fixture: returned DecoderEmbeddings · level recorded 2026-09-22
MAEOutput torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · a9991ea23ae0f3d2 · report fixture: returned MAEOutput · level recorded 2026-09-22
PatchEmbeddings in 5 papers torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · 8163b722029972c0 · report fixture: returned PatchEmbeddings · level recorded 2026-09-22
PatchEmbeddingsOutput torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · bb30b6d29305dccf · report fixture: returned PatchEmbeddingsOutput · level recorded 2026-09-22
RandomMaskingOutput torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · c2ccb58b26b80780 · report fixture: returned RandomMaskingOutput · level recorded 2026-09-22
TransformerOutput in 5 papers torchmultimodal/models/masked_auto_encoder/model.py ran BSD-3-Clause (permissive) · 56d769a7351c787e · report fixture: returned TransformerOutput · level recorded 2026-09-22
_random_masking_1d torchmultimodal/models/masked_auto_encoder/model.py ran; the contract check could not run (RAISES) fingerprinted BSD-3-Clause (permissive) · cad22d0081516d4a · report fixture: signature x:Tensor/4/float, mask_ratio:float/0/float, num_patches_h:int/0/int, num_patches_w:int/0/int · returned tuple · level recorded 2026-09-22
get_1d_sin_cos_embeddings torchmultimodal/models/masked_auto_encoder/model.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 3dc442f442bab69d · report fixture: signature embed_dim:int/0/int, positions:Tensor/1/float · returned Tensor · level recorded 2026-09-22
get_2d_sin_cos_embeddings torchmultimodal/models/masked_auto_encoder/model.py ran; the contract check could not run (RAISES) fingerprinted BSD-3-Clause (permissive) · 931261dd3b92624d · report fixture: signature embed_dim:int/0/int, input_size:tuple/1/int, include_cls_embed:bool/0/bool · returned Tensor · level recorded 2026-09-22
random_masking in 13 papers torchmultimodal/models/masked_auto_encoder/model.py ran; the contract check could not run (RAISES) fingerprinted BSD-3-Clause (permissive) · 6c5d9dcc5cf2ba42 · report fixture: signature x:Tensor/3/float, mask_ratio:float/0/float · returned RandomMaskingOutput · level recorded 2026-09-22
random_masking_2d torchmultimodal/models/masked_auto_encoder/model.py ran; the contract check could not run (RAISES) BSD-3-Clause (permissive) · ba9d7aee607505ff · report fixture: signature x:Tensor/3/float, mask_ratio_h:float/0/float, mask_ratio_w:float/0/float, num_patches_h:int/0/int, num_patches_w:int/0/int · returned Tensor · level recorded 2026-09-22
MaskedAutoEncoder torchmultimodal/models/masked_auto_encoder/model.py unverified BSD-3-Clause (permissive) · f8e7dc86b0afa131 · report
facebookresearch/vip-mae community (archive-listed) 1 sample, 0 ran · 1 unverified
MaskedAutoencoderViT in 14 papers models_mae.py unverified licence not identified · pointer only · aaad170bbdcb0282 · report
guilk/vlc community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vlc/modules/mae_transformer.py ran fingerprinted no licence file found · pointer only · b1605707f77d1785 · report fixture: signature x:Tensor/3/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
vlc/modules/mae_transformer.py ran no licence file found · pointer only · ad2aca1970e4adb8 · report fixture: returned Block · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
vlc/modules/mae_transformer.py ran no licence file found · pointer only · aca1bd49f0338dbf · report fixture: returned PatchEmbed · level recorded 2026-09-22
MaskedAutoencoderViT in 14 papers vlc/modules/mae_transformer.py unverified no licence file found · pointer only · aee0709299e0074e · report
hkbu-vscomputing/2022_mm_dmae-mocap community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model/dmae.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 331e0a44942a0951 · report fixture: returned Attention · level recorded 2026-09-22
DMaeV5 model/dmae.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 497da9d8d920d347 · report fixture: returned DMaeV5 · level recorded 2026-09-22
Transformer in 173 papers model/dmae.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 4ee06daa6459c4aa · report fixture: returned Transformer · level recorded 2026-09-22
isaaccorley/hydro-foundation-model community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
SimMIM src/models/simmim.py ran MIT (permissive) · ea3ec9aaa022ab81 · report fixture: signature x:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
norm_targets src/models/simmim.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · c438fe1587079a16 · report fixture: signature targets:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded 2026-09-22
islamosmanubc/MedMAE community (archive-listed) 1 sample, 0 ran · 1 unverified
MaskedAutoencoderViT in 14 papers code/models_mae.py unverified no licence file found · pointer only · 6d8df0e8713ee9e0 · report
keytoyze/visionts community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MaskedAutoencoderViT in 14 papers visionts/models_mae.py ran · metamorphic tier: deterministic MIT (permissive) · 5c85cd8b5812d34f · report fixture: returned MaskedAutoencoderViT · level recorded 2026-09-22
liujiyuan13/MAE-code community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 5671450eaed4b12b · report fixture: returned Attention · level recorded 2026-09-22
Transformer in 173 papers model.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 2535ae01b09ade02 · report fixture: returned Transformer · level recorded 2026-09-22
MAE in 46 papers model.py unverified GPL-3.0 (copyleft) · pointer only · 1caa82740b24080e · report
mx-mark/videotransformer-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RandomMaskGenerator mask_generator.py ran · metamorphic tier: well formed no licence file found · pointer only · db04c09ee238a7d0 · report fixture: returned ndarray · level recorded 2026-09-22
nasa-impact/hls-foundation-os community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
geospatial_fm/geospatial_fm.py ran Apache-2.0 (permissive) · f6ed4fbd11e09648 · report fixture: signature embed_dim:int/0/int, pos:Tensor/1/float · returned ndarray · level recorded 2026-09-24
get_3d_sincos_pos_embed in 16 papers geospatial_fm/geospatial_fm.py ran Apache-2.0 (permissive) · c6230d72998a4af2 · report fixture: signature embed_dim:int/0/int, grid_size:tuple/1/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-24
pengzhiliang/MAE-pytorch community (archive-listed) 3 samples, 0 ran · 3 unverified
PretrainVisionTransformer in 6 papers modeling_pretrain.py unverified no licence file found · pointer only · e9ab3ea658aaf2ac · report
PretrainVisionTransformerDecoder modeling_pretrain.py unverified no licence file found · pointer only · 227479361f4b8896 · report
PretrainVisionTransformerEncoder in 5 papers modeling_pretrain.py unverified no licence file found · pointer only · 90a4425d6dd96eba · report
qiaopTDUN/mae-repo community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MAE in 46 papers vit_pytorch/mae.py ran no licence file found · pointer only · 62051d3ebdd50d03 · report fixture: returned MAE · level recorded 2026-09-22
virajprabhu/pacmac community (archive-listed) 1 sample, 0 ran · 1 unverified
MaskedAutoencoderViT in 14 papers models_mae.py unverified licence not identified · pointer only · c24c07e5963dbcef · report
wangsr126/mae-lite community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
projects/mae_lite/models_mae.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 52e133864e98cbdc · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
projects/mae_lite/models_mae.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f85de2d93369d9d8 · report fixture: returned Block · level recorded 2026-09-22
MaskedAutoencoderViT in 14 papers projects/mae_lite/models_mae.py unverified Apache-2.0 (permissive) · 3ad95a45a1da4292 · report
yangsun22/tc-moa community (archive-listed) 18 samples, 12 ran (5 instrument-failed) · 6 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model/ViT_MAE.py ran · metamorphic tier: deterministic no licence file found · pointer only · 861a1945b7d265b5 · report fixture: returned Block · level recorded 2026-09-22
MEF_MSSSIM model/ViT_MAE.py ran · metamorphic tier: deterministic no licence file found · pointer only · d20317addad2ec2a · report fixture: returned MEF_MSSSIM · level recorded 2026-09-22
MLP in 375 papers model/ViT_MAE.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bc87b313b8223daa · report fixture: returned MLP · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
model/ViT_MAE.py ran · metamorphic tier: deterministic no licence file found · pointer only · 87472fa3925de39b · report fixture: returned PatchEmbed · level recorded 2026-09-22
Relative_Position_Layer model/ViT_MAE.py ran · metamorphic tier: deterministic no licence file found · pointer only · 674cd8263656f0a9 · report fixture: returned Relative_Position_Layer · level recorded 2026-09-22
SparseDispatcher in 7 papers model/ViT_MAE.py ran no licence file found · pointer only · 15b2b3f169df4432 · report fixture: returned SparseDispatcher · level recorded 2026-09-22
_mef_ssim model/ViT_MAE.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · a02c6d0a4898ab3c · report fixture: signature X:Tensor/3/float, Ys:Tensor/4/float, window:Tensor/4/float, ws:int/0/int, denom_g:float/0/float, denom_l:float/0/float, C1:float/0/float, C2:float/0/float, is_lum:bool/0/bool, full:bool/0/bool · returned Tensor · level recorded 2026-09-22
create_window in 82 papers model/ViT_MAE.py ran · honoured contract fingerprinted no licence file found · pointer only · ea765f7aef3e0254 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-22
mef_msssim model/ViT_MAE.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8641710492e3764e · report fixture: signature X:Tensor/4/float, Ys:Tensor/4/float, window:Tensor/4/float, ws:int/0/int, denom_g:float/0/float, denom_l:float/0/float, C1:float/0/float, C2:float/0/float, is_lum:bool/0/bool · returned Tensor · level recorded 2026-09-22
recover_Norm model/ViT_MAE.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 354c35b22458297a · report fixture: returned Tensor · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model/ViT_MAE.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · b206cc7bb36ab3f9 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers model/ViT_MAE.py ran · our draft was wrong no licence file found · pointer only · d12c21909a77aa54 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
BiMixtureOfAdapters model/ViT_MAE.py unverified no licence file found · pointer only · 920f7876acd40a63 · report
ConvFusionLayer model/ViT_MAE.py unverified no licence file found · pointer only · e1db3c67b651e9d6 · report
MMoE model/ViT_MAE.py unverified no licence file found · pointer only · df9090581a1cd535 · report
MaskedAutoencoderViT in 14 papers model/ViT_MAE.py unverified no licence file found · pointer only · 69fcb0b19116792a · report
get_2d_sincos_pos_embed in 170 papers model/ViT_MAE.py unverified no licence file found · pointer only · 43ab33710deb02f8 · report
yifanzhang-pro/m-mae community (archive-listed) 1 sample, 0 ran · 1 unverified
MaskedAutoencoderViT in 14 papers models_mae.py unverified no licence file found · pointer only · a884a29cbdfbf1c0 · report
zinengtang/tvlt community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
compute_mae_video model/modules/objectives.py ran · our draft was wrong MIT (permissive) · b6e1b0c89f370eb3 · report fixture: signature pl_module:callable/0/?, batch:dict/0/?, patch_size:int/0/int, num_patches:int/0/int · returned dict · level recorded 2026-09-22
patchify_video model/modules/objectives.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · bacc63cd8c3fe982 · report fixture: signature vids:Tensor/5/float, p:int/0/int · returned Tensor · level recorded 2026-09-22
PatrickHua/SimpleMAE community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
MAE in 46 papers mae.py ran · metamorphic tier: deterministic no licence file found · pointer only · e0ce63efd1bd3605 · report fixture: returned MAE · level recorded 2026-09-22
PatchShuffler mae.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4e3aa5c38953cd03 · report fixture: returned PatchShuffler · level recorded 2026-09-22
Transformer in 173 papers mae.py ran · metamorphic tier: deterministic no licence file found · pointer only · f510e0f909e0f1d0 · report fixture: returned Transformer · level recorded 2026-09-22
positional_encoding in 63 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input
mae.py ran · honoured contract fingerprinted no licence file found · pointer only · 23e046b80e6b93a5 · report fixture: signature d_model:int/0/int, max_len:int/0/int · returned Tensor · level recorded 2026-09-22
alibaba/EasyCV community (archive-listed) 2 samples, 0 ran · 2 unverified
MaskedAutoencoderViT in 14 papers easycv/models/backbones/mae_vit_transformer.py unverified Apache-2.0 (permissive) · 4265e07807c81d08 · report
Registry in 34 papers easycv/models/backbones/mae_vit_transformer.py unverified Apache-2.0 (permissive) · c0e3084b8e16dcc1 · report
yangyucheng000/mae community (archive-listed) 9 samples, 9 ran (1 instrument-failed) · 0 unverified
check_obs_url src/helper.py ran Apache-2.0 (permissive) · d5d542acf05a4fd3 · report fixture: signature url:str/0/str · returned bool · level recorded 2026-09-24
get_logger in 383 papers src/logger.py ran Apache-2.0 (permissive) · 8765fe83bed1a28f · report fixture: signature path:str/0/str, rank:int/0/int · returned LOGGER · level recorded 2026-09-24
mixup_target in 22 papers src/datasets/mixup.py ran Apache-2.0 (permissive) · 8d6695b3b7693e8a · report fixture: signature target:ndarray/1/int, num_classes:int/0/int, lam:float/0/float, smoothing:float/0/float · returned ndarray · level recorded 2026-09-24
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
src/datasets/mixup.py ran Apache-2.0 (permissive) · 500863dca85164af · report fixture: signature x:ndarray/1/int, num_classes:int/0/int, on_value:float/0/float, off_value:float/0/float · returned ndarray · level recorded 2026-09-24
rand_bbox in 63 papers src/datasets/mixup.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 3913c620f6926f42 · report fixture: signature img_shape:tuple/1/int, lam:float/0/float, margin:float/0/float, count:NoneType/0/? · returned tuple · level recorded 2026-09-24
shear_x in 43 papers src/datasets/auto_augment.py ran Apache-2.0 (permissive) · 836abfc1dec21f54 · report fixture: signature img:Image/0/?, factor:float/0/float, fillcolor:tuple/1/int, resample:int/0/int · returned Image · level recorded 2026-09-24
shear_y in 37 papers src/datasets/auto_augment.py ran Apache-2.0 (permissive) · f72f09eb9fd3f148 · report fixture: signature img:Image/0/?, factor:float/0/float, fillcolor:tuple/1/int, resample:int/0/int · returned Image · level recorded 2026-09-24
sync_trans src/helper.py ran Apache-2.0 (permissive) · 1917cd1b8b1483d5 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-24
translate_x_rel in 27 papers src/datasets/auto_augment.py ran Apache-2.0 (permissive) · f3b161d964735796 · report fixture: signature img:Image/0/?, pct:float/0/float, fillcolor:NoneType/0/?, resample:int/0/int · returned Image · level recorded 2026-09-24
yongyupei/papers_with_examps community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
translate_x_rel in 27 papers mae/src/process_datasets/auto_augment.py ran Apache-2.0 (permissive) · 1644b5d70651bbcf · report fixture: signature img:Image/0/?, pct:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
shear_x in 43 papers mae/src/process_datasets/auto_augment.py unverified Apache-2.0 (permissive) · 328334d15e09e000 · report
shear_y in 37 papers mae/src/process_datasets/auto_augment.py unverified Apache-2.0 (permissive) · cdd7912370ff7225 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded

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.

25 assemblies on this paper: 25 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

25 sibling assemblies for Masked Autoencoders (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 25 sibling assemblies; the other 13 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 21 bricks; individually on a fixture: 13 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · 69fcb0b19116792a
  2. BiMixtureOfAdapters helper · level 0 · unverified · 920f7876acd40a63
  3. Block helper · level 1 · ran · 861a1945b7d265b5
  4. ConvFusionLayer helper · level 0 · unverified · e1db3c67b651e9d6
  5. MEF_MSSSIM helper · level 1 · ran · d20317addad2ec2a
  6. PatchEmbed model · level 1 · ran · 87472fa3925de39b
  7. Relative_Position_Layer helper · level 1 · ran · 674cd8263656f0a9
  8. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  9. recover_Norm helper · level 1 · ran; the contract check could not run (RAISES) · 354c35b22458297a
  10. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · b206cc7bb36ab3f9
  11. MMoE helper · level 0 · unverified · df9090581a1cd535
  12. Attention helper · level 0 · unverified · ab6e3fb020aef3ab
  13. window_reverse helper · level 1 · ran · our draft was wrong · d12c21909a77aa54
  14. create_window helper · level 1 · ran · honoured contract · ea765f7aef3e0254
  15. mef_msssim helper · level 1 · ran; the contract check could not run (RAISES) · 8641710492e3764e
  16. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  17. MLP helper · level 1 · ran · bc87b313b8223daa
  18. SparseDispatcher helper · level 1 · ran · 15b2b3f169df4432
  19. gaussian helper · level 1 · ran · honoured contract · c56b7ef16f309a45
  20. _mef_ssim helper · level 1 · ran; the contract check could not run (RAISES) · a02c6d0a4898ab3c
  21. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 12 bricks; individually on a fixture: 7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · db65696502e25065
  2. Decoder model · level 0 · unverified · b892a94c4303b6e7
  3. Encoder model · level 0 · unverified · 9d6e5fd05d104462
  4. Block model · level 0 · unverified · e6f87d41087f7d2d
  5. Mask helper · level 0 · unverified · 9ded34638fb55197
  6. PatchEmbed helper · level 1 · ran · 8c15bb7018339540
  7. Attention helper · level 1 · ran · 2caebdfa70d265d1
  8. DropPath helper · level 1 · ran · a84a5b2f271cf15c
  9. TransformerMLP model · level 1 · ran · d250b23f4ed3fd00
  10. DepthwiseConv2D helper · level 1 · ran · 1eb614b14acb62c8
  11. sincosemb1d helper · level 1 · ran; the contract check could not run (RAISES) · ba4526d5e3418ddb
  12. sincosposemb helper · level 1 · ran · honoured contract · 3b6e902cfca4fc8a

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 5 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 25 siblings

  1. DMaeV5 entry · level 1 · ran · 497da9d8d920d347
  2. Transformer helper · level 1 · ran · 4ee06daa6459c4aa
  3. Attention helper · level 1 · ran · 331e0a44942a0951
  4. FeedForward helper · level 1 · ran · c17d96c99b861de1
  5. PreNorm helper · level 1 · ran · 005532cda6b215dd

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 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 25 siblings

  1. MAE entry · level 0 · unverified · 1caa82740b24080e
  2. Transformer model · level 1 · ran · 2535ae01b09ade02
  3. Attention model · level 1 · ran · 5671450eaed4b12b
  4. FeedForward model · level 1 · ran · c17d96c99b861de1
  5. PreNorm model · level 1 · ran · 005532cda6b215dd

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 6 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · 3ad95a45a1da4292
  2. Block model · level 1 · ran · f85de2d93369d9d8
  3. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  4. Attention model · level 1 · ran · 52e133864e98cbdc
  5. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  6. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 4 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 1 · ran · 5c85cd8b5812d34f
  2. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · 5a37690a13a6157d
  3. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 2884deadbb637c3e
  4. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 5c8ea92d43ead77d

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

one of 25 siblings

  1. MAE entry · level 1 · ran · e0ce63efd1bd3605
  2. PatchShuffler helper · level 1 · ran · 4e3aa5c38953cd03
  3. Transformer model · level 1 · ran · f510e0f909e0f1d0
  4. positional_encoding helper · level 1 · ran · honoured contract · 23e046b80e6b93a5

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · a884a29cbdfbf1c0
  2. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  3. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  4. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 13 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) · 12 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 25 siblings

  1. MaskedAutoencoderModel entry · level 0 · unverified · 8e71ab74b3539260
  2. LinearDecoder model · level 1 · ran · 8c2a5e9356370f98
  3. VisionTransformerDecoder model · level 0 · unverified · 65d6b4d0f5c0932c
  4. build_encoder helper · level 0 · unverified · e18efe0723eb391d
  5. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  6. VisionTransformerMAE model · level 0 · unverified · 7b0c5df25df03a0f
  7. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  8. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c
  9. vit_base_patch16 helper · level 0 · unverified · e74f91045366913e
  10. vit_huge_patch14 helper · level 0 · unverified · 16f4365f89fc1383
  11. vit_large_patch16 helper · level 0 · unverified · 404d47a8e8939ea1
  12. vit_small_patch16 helper · level 0 · unverified · bd06f7ac78d039d0
  13. vit_tiny_patch16 helper · level 0 · unverified · d1699368ffaa6920

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 5 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) · 1 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · aee0709299e0074e
  2. Block model · level 1 · ran · ad2aca1970e4adb8
  3. PatchEmbed model · level 1 · ran · aca1bd49f0338dbf
  4. Attention model · level 1 · ran · b1605707f77d1785
  5. Mlp model · level 1 · ran · a1715055832f71fd

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 12 bricks; individually on a fixture: 11 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; 5 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. MaskedAutoEncoder entry · level 0 · unverified · f8e7dc86b0afa131
  2. DecoderEmbeddings model · level 1 · ran · 50340b2a447969fb
  3. MAEOutput helper · level 1 · ran · a9991ea23ae0f3d2
  4. PatchEmbeddings helper · level 1 · ran · 8163b722029972c0
  5. get_2d_sin_cos_embeddings helper · level 1 · ran; the contract check could not run (RAISES) · 931261dd3b92624d
  6. TransformerOutput helper · level 1 · ran · 56d769a7351c787e
  7. PatchEmbeddingsOutput helper · level 1 · ran · bb30b6d29305dccf
  8. random_masking helper · level 1 · ran; the contract check could not run (RAISES) · 6c5d9dcc5cf2ba42
  9. random_masking_2d helper · level 1 · ran; the contract check could not run (RAISES) · ba9d7aee607505ff
  10. get_1d_sin_cos_embeddings helper · level 1 · ran · our draft was wrong · 3dc442f442bab69d
  11. RandomMaskingOutput helper · level 1 · ran · c2ccb58b26b80780
  12. _random_masking_1d helper · level 1 · ran; the contract check could not run (RAISES) · cad22d0081516d4a

harvested Assembly for Masked Autoencoders (graph method: Masked Autoencoders). 2 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) · 0 unverified. The assembly has not been run end-to-end.

one of 25 siblings

  1. compute_mae_video entry · level 1 · ran · our draft was wrong · b6e1b0c89f370eb3
  2. patchify_video helper · level 1 · ran; the contract check could not run (RAISES) · bacc63cd8c3fe982
  1. MaskedAutoencoderViT · 7e2adb19f7027bd3 · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MAE_ViT · 8807e0a8b096e8e6 · 6 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 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 · assemblies[13] in the JSON twin
  3. MaskedAutoencoderViT · 933cf4604a36aa2c · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. ViTMAEForPreTraining · 944c0465d9194b8f · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. MAEVisionTransformers · b0f70e38695384d4 · 16 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. MAE · b4677c108b559bd2 · 5 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. PretrainVisionTransformer · bb977fa5dc091c88 · 10 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. PretrainVisionTransformer · ce8daf4efcad54b0 · 11 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. RandomMaskGenerator · d14e56550cbd3e73 · 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 · assemblies[20] in the JSON twin
  10. MaskedAutoencoderViT · d766348206ea735f · 8 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. MaskedAutoencoderViT · dd4c3c143c8090df · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. MaskedAutoencoderViT · e191f88ecd74e77d · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. SimMIM · f8cb3ef4cf1f29b7 · 2 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[24] 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="2111.06377") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderDomain GeneralizationImage ClassificationObject DetectionOut-of-Distribution GeneralizationSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A MAE (ViT-H, 448) Top-1 accuracy % 76.7 #6 of 39 Archive leaderboard report
Domain Generalization ImageNet-C MAE (ViT-H) Number of params 632M #6 of 47 Archive leaderboard report
Domain Generalization ImageNet-C MAE (ViT-H) mean Corruption Error (mCE) 33.8 #6 of 47 Archive leaderboard report
Domain Generalization ImageNet-R MAE (ViT-H, 448) Top-1 Error Rate 33.5 #10 of 39 Archive leaderboard report
Domain Generalization ImageNet-Sketch MAE (ViT-H, 448) Top-1 accuracy 50.9 #10 of 20 Archive leaderboard report
Image Classification ImageNet MAE (ViT-H, 448) Number of params 656M #73 of 1060 Archive leaderboard report
Image Classification ImageNet MAE (ViT-H, 448) Top 1 Accuracy 87.8% #73 of 1060 Archive leaderboard report
Image Classification ImageNet MAE (ViT-H) Top 1 Accuracy 86.9% #114 of 1060 Archive leaderboard report
Image Classification ImageNet MAE (ViT-L) Top 1 Accuracy 85.9% #185 of 1060 Archive leaderboard report
Image Classification ImageNet MAE (ViT-L) Top 1 Accuracy 83.6% #408 of 1060 Archive leaderboard report
Image Classification OmniBenchmark MAE Average Top-1 Accuracy 30.6 #21 of 22 Archive leaderboard report
Image Classification Places205 MAE (ViT-H, 448) Top 1 Accuracy 66.8 #5 of 15 Archive leaderboard report
Image Classification Places365-Standard MAE (ViT-H, 448) Top 1 Accuracy 60.3 #3 of 4 Archive leaderboard report
Image Classification iNaturalist MAE (ViT-H, 448) Top 1 Accuracy 83.4 #3 of 19 Archive leaderboard report
Image Classification iNaturalist 2018 MAE (ViT-H, 448) Top-1 Accuracy 86.8% #7 of 60 Archive leaderboard report
Image Classification iNaturalist 2019 MAE (ViT-H, 448) Top-1 Accuracy 88.3 #2 of 22 Archive leaderboard report
Object Detection COCO minival MAE (ViT-L, Mask R-CNN) box AP 53.3 #61 of 220 Archive leaderboard report
Object Detection COCO minival MAE (ViT-B, Mask R-CNN) box AP 50.3 #79 of 220 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-H) Number of Params 700M #59 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-H) Top 1 Accuracy 76.6% #59 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-L) Number of Params 306M #66 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-L) Top 1 Accuracy 75.8% #66 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-B) Number of Params 80M #107 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet MAE (ViT-B) Top 1 Accuracy 68.0% #107 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MAE (ViT-H/14, 448) Number of Params 632M #7 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MAE (ViT-H/14, 448) Top 1 Accuracy 87.8% #7 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MAE (ViT-H/14) Top 1 Accuracy 86.9% #11 of 65 Archive leaderboard report
Semantic Segmentation ADE20K MAE (ViT-L, UperNet) Validation mIoU 53.6 #78 of 235 Archive leaderboard report
Semantic Segmentation ADE20K MAE (ViT-B, UperNet) Validation mIoU 48.1 #154 of 235 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL+FT, mmseg) mIoU (test) 61.2 #4 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL+FT, mmseg) mIoU (val) 61.6 #4 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL+FT) mIoU (test) 60.2 #5 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL+FT) mIoU (val) 61.0 #5 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL, mmseg) mIoU (test) 40.3 #17 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL, mmseg) mIoU (val) 40.0 #17 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL) mIoU (test) 37.0 #18 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S MAE (ViT-B/16, 224x224, SSL) mIoU (val) 38.3 #18 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: MAE

CV-MIMMAE

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