Papers › Training data-efficient image transformers & distillation through attention

Training data-efficient image transformers & distillation through attention

23 Dec 2020arXiv:2012.12877archive 2025-07-28

Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

PaperPDFCodeCode 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/deit) is linked to this paper; the 19 samples below come from 9 community repositories. Syntology harvested code from facebookresearch/deit for 2 other papers.

facebookresearch/deit: Syntology's graph links these samples to Augmenting Convolutional networks with attention-based aggregation (arXiv:2112.13692; that paper's own run record: 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) and Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 19 code samples harvested from 9 repositories linked to this paper: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 19 samples from 9 repositories, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 21 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.

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

facebookresearch/deit officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Augmenting Convolutional networks with attention-based aggregation (arXiv:2112.13692; that paper's own run record: 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) and Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
rwightman/pytorch-image-models mentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Burf/VisionTransformer-Tensorflow2 mentioned on GitHubtfSyntology: 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
IMvision12/keras-vision-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
TACJu/TransFG mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
UdbhavPrasad072300/Transformer-Implementations mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
affjljoo3581/deit3-jax mentioned on GitHubjaxSyntology: 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
ahmedelmahy/myownvit mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (arXiv:2101.11986; that paper's own run record: 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified), CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification (arXiv:2103.14899; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 1 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified), CvT: Introducing Convolutions to Vision Transformers (arXiv:2103.15808; that paper's own run record: 39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
aiot-mlsys-lab/famba-v mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion (arXiv:2409.09808; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
alessiomora/unlearning_fl mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (arXiv:2105.15203; that paper's own run record: 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
asrafulashiq/deit-custom mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
bshantam97/Attention_Based_Networks 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
cogtoolslab/physics-benchmarking-neurips2021 mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Physion: Evaluating Physical Prediction from Vision in Humans and Machines (arXiv:2106.08261; 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
gatech-eic/vitcod mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference (arXiv:2104.01136; that paper's own run record: 23 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
holdfire/CLS mentioned on GitHubpytorchSyntology: not harvested report
holdfire/FAS mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
hustvl/vim mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jacobgil/vit-explain mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Quantifying Attention Flow in Transformers (arXiv:2005.00928; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 6 unverified) and 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
liuxingwt/CLS mentioned on GitHubpytorchSyntology: not harvested report
moein-shariatnia/Pix2Seq mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nus-hpc-ai-lab/dyvm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mamba: Linear-Time Sequence Modeling with Selective State Spaces (arXiv:2312.00752; that paper's own run record: 28 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 34 unverified); nothing checks that they implement this paper's method. report
omihub777/vit-cifar mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
s-chh/patchrot mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PatchRot: A Self-Supervised Technique for Training Vision Transformers (arXiv:2210.15722; that paper's own run record: 6 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; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
skchen1993/TrangFG 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
smu-ivpl/DeepfakeDetection mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The DeepFake Detection Challenge (DFDC) Dataset (arXiv:2006.07397; 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) · 2 unverified) and 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
tianhai123/vit-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (arXiv:2101.11986; that paper's own run record: 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
ttt496/vit-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (arXiv:2101.11986; that paper's own run record: 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified), Rethinking Spatial Dimensions of Vision Transformers (arXiv:2103.16302; that paper's own run record: 10 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; 0 where Syntology's instrument failed) · 10 unverified) and LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference (arXiv:2104.01136; that paper's own run record: 23 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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
zhuhanqing/lightening-transformer mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
BR-IDL/PaddleViT paddleSyntology: not harvested report
Oguzhanercan/Vision-Transformers Syntology: not harvested report
PaddlePaddle/PLSC paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Token Merging: Your ViT But Faster (arXiv:2210.09461; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
alibaba/EasyCV pytorchSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report
code-implementation1/Code1 mindsporeSyntology: 1 sample, 0 ran · 1 unverified report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
open-edge-platform/training_extensions pytorchApache-2.0Syntology: not harvested 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

19 samples harvested: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
8ran
7unverified

Licence: 3 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 9 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 whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “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.

TACJu/TransFG community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
con_loss models/modeling.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · c1c79ef7fd065038 · report fixture: signature features:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
UdbhavPrasad072300/Transformer-Implementations community (archive-listed) 1 sample, 0 ran · 1 unverified
DeiT transformer_package/models/transformer.py unverified MIT (permissive) · 4eae8cfd26a7bed5 · report
asrafulashiq/deit-custom community (archive-listed) 1 sample, 0 ran · 1 unverified
DistilledVisionTransformer models.py unverified Apache-2.0 (permissive) · 2de7c7e2fe313b48 · report
holdfire/FAS community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DistilledVisionTransformer models/deit.py ran no licence file found · pointer only · fee0f891e0558ff8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
hustvl/vim community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DistillationLoss vim/losses.py ran Apache-2.0 (permissive) · b42ba639d4f94082 · report fixture: returned DistillationLoss · level recorded 2026-09-22
moein-shariatnia/Pix2Seq community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Encoder in 278 papers model.py ran MIT (permissive) · e089d779e4638b42 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
omihub777/vit-cifar community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
MultiHeadSelfAttention in 17 papers dw_vit.py ran · metamorphic tier: invariant MIT (permissive) · 295ab55989f9e8fe · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TransformerEncoder in 96 papers dw_vit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 9e38671b1e2518ec · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DepthwiseViT dw_vit.py unverified MIT (permissive) · fa8c4e7bc2b8d354 · report
alibaba/EasyCV community (archive-listed) 9 samples, 6 ran (3 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
easycv/models/backbones/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · c0bfabc05e380222 · report fixture: signature x:Tensor/3/float, rel_pos_bias:NoneType/0/? · returned tuple · 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 this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
easycv/models/backbones/vision_transformer.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · c713760d26bf0a45 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Mlp in 102 papers easycv/models/backbones/vision_transformer.py ran Apache-2.0 (permissive) · 64505a0b6aa5e3d4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
_no_grad_trunc_normal_ in 16 papers
census: 16 implementations from 16 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
easycv/models/backbones/vision_transformer.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 5bcbd988b672cf32 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
hydra easycv/models/backbones/vision_transformer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c4a17f13fadc2630 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float · returned Tensor · level recorded 2026-09-24
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
easycv/models/backbones/vision_transformer.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 462cf9fa4898bc51 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
ValueError easycv/models/backbones/vision_transformer.py unverified Apache-2.0 (permissive) · c152c68202903a9f · report
VisionTransformer in 53 papers easycv/models/backbones/vision_transformer.py unverified Apache-2.0 (permissive) · a4ea24ce126312f8 · report
code-implementation1/Code1 community (archive-listed) 1 sample, 0 ran · 1 unverified
_add_distilation_arguments DeiT/src/args.py unverified no licence file found · pointer only · d90ec8f4e83b1d6a · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for token-based distillation (graph method: token-based distillation). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. DistilledVisionTransformer entry · level 0 · unverified · 2de7c7e2fe313b48

harvested Assembly for token-based distillation (graph method: token-based distillation). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. _add_distilation_arguments entry · level 0 · unverified · d90ec8f4e83b1d6a

harvested Assembly for token-based distillation (graph method: token-based distillation). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. con_loss entry · level 1 · ran · honoured contract · c1c79ef7fd065038

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

one of 9 siblings

  1. DistilledVisionTransformer entry · level 1 · ran · fee0f891e0558ff8

harvested Assembly for token-based distillation (graph method: token-based distillation). 3 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) · 1 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 9 siblings

  1. DeiT entry · level 0 · unverified · 4eae8cfd26a7bed5
  2. VisionEncoder model · level 1 · ran · bacfe561400c3879
  3. MultiHeadAttention helper · level 1 · ran · 61787a7f1ca16779

harvested Assembly for token-based distillation (graph method: token-based distillation). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. DistillationLoss entry · level 1 · ran · b42ba639d4f94082

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

one of 9 siblings

  1. Encoder entry · level 1 · ran · e089d779e4638b42

harvested Assembly for token-based distillation (graph method: token-based distillation). 15 bricks; individually on a fixture: 11 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. VisionTransformer entry · level 0 · unverified · a4ea24ce126312f8
  2. Block model · level 0 · unverified · bc7c311c2770067a
  3. PatchEmbed model · level 1 · ran · 9187f42531072c00
  4. ValueError helper · level 0 · unverified · c152c68202903a9f
  5. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · 462cf9fa4898bc51
  6. Attention model · level 1 · ran · c0bfabc05e380222
  7. DropPath helper · level 1 · ran · c713760d26bf0a45
  8. Mlp helper · level 1 · ran · 64505a0b6aa5e3d4
  9. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  10. BaseError helper · level 1 · ran · 6f3e4e43ff039081
  11. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · 5bcbd988b672cf32
  12. hydra helper · level 1 · ran · our draft was wrong · c4a17f13fadc2630
  13. KeyError helper · level 1 · ran · cd97bea208feabb0
  14. Registry helper · level 0 · unverified · c0e3084b8e16dcc1
  15. TypeError helper · level 1 · ran · b1bd1c1bd350e556

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

one of 9 siblings

  1. DepthwiseViT entry · level 0 · unverified · fa8c4e7bc2b8d354
  2. TransformerEncoder model · level 1 · ran · 9e38671b1e2518ec
  3. MultiHeadSelfAttention helper · level 1 · ran · 295ab55989f9e8fe

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="2012.12877") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document Image ClassificationDocument Layout AnalysisEfficient ViTsFine-Grained Image ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Image Classification RVL-CDIP DeiT-B Accuracy 90.32% #30 of 31 Archive leaderboard report
Document Image Classification RVL-CDIP DeiT-B Parameters 87M #30 of 31 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B Figure 0.957 #10 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B List 0.921 #10 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B Overall 0.932 #10 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B Table 0.972 #10 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B Text 0.934 #10 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val DeiT-B Title 0.874 #10 of 15 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) Base (DeiT-S) GFLOPs 4.6 #12 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) Base (DeiT-S) Top 1 Accuracy 79.8 #12 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) Base (DeiT-T) GFLOPs 1.2 #7 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) Base (DeiT-T) Top 1 Accuracy 72.2 #7 of 22 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers DeiT-B Accuracy 98.8% #10 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers DeiT-B PARAMS 86M #10 of 25 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars DeiT-B Accuracy 93.3% #65 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars DeiT-B PARAMS 86M #65 of 83 Archive leaderboard report
Image Classification CIFAR-10 DeiT-B Percentage correct 99.1 #14 of 265 Archive leaderboard report
Image Classification CIFAR-100 DeiT-B PARAMS 86M #22 of 211 Archive leaderboard report
Image Classification CIFAR-100 DeiT-B Percentage correct 90.8 #22 of 211 Archive leaderboard report
Image Classification Flowers-102 DeiT-B Accuracy 98.8% #21 of 52 Archive leaderboard report
Image Classification Flowers-102 DeiT-B PARAMS 86M #21 of 52 Archive leaderboard report
Image Classification ImageNet DeiT-B 384 Number of params 87M #251 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B 384 Top 1 Accuracy 85.2% #251 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Number of params 86M #341 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Top 1 Accuracy 84.2% #341 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Number of params 22M #524 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Top 1 Accuracy 82.6% #524 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Number of params 5M #910 of 1060 Archive leaderboard report
Image Classification ImageNet DeiT-B Top 1 Accuracy 76.6% #910 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-B-384 Accuracy 89.3% #24 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-B-384 Params 86M #24 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-B Accuracy 88.7% #26 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-B Params 86M #26 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-S Accuracy 86.8% #36 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-S Params 22M #36 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-Ti Accuracy 82.1% #49 of 57 Archive leaderboard report
Image Classification ImageNet ReaL DeiT-Ti Params 5M #49 of 57 Archive leaderboard report
Image Classification iNaturalist 2018 DeiT-B Top-1 Accuracy 79.5% #18 of 60 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

AdamWAttentionAttention DropoutCutMixDeiTDense ConnectionsDropoutFeedforward NetworkFixResLabel SmoothingLinear LayerMixupMulti-Head AttentionRandAugmentSoftmaxStochastic DepthWeight Decay

3 archive method tags without a method page not shown.

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