Papers › Training data-efficient image transformers & distillation through attention
Training data-efficient image transformers & distillation through attention
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2012.12877")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2012.12877", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2012.12877")
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:
- facebookresearch/deit, official repository: harvested for 2 other papers, listed under the repository
- rwightman/pytorch-image-models, named in the paper: harvested for another paper, listed under the repository
- Burf/VisionTransformer-Tensorflow2, community (archive-listed): harvested for another paper, listed under the repository
- IMvision12/keras-vision-models, community (archive-listed): harvested for another paper, listed under the repository
- affjljoo3581/deit3-jax, community (archive-listed): harvested for another paper, listed under the repository
- ahmedelmahy/myownvit, community (archive-listed): harvested for 5 other papers, listed under the repository
- aiot-mlsys-lab/famba-v, community (archive-listed): harvested for another paper, listed under the repository
- alessiomora/unlearning_fl, community (archive-listed): harvested for another paper, listed under the repository
- bshantam97/Attention_Based_Networks, community (archive-listed): harvested for another paper, listed under the repository
- cogtoolslab/physics-benchmarking-neurips2021, community (archive-listed): harvested for another paper, listed under the repository
- gatech-eic/vitcod, community (archive-listed): harvested for another paper, listed under the repository
- huggingface/transformers, community (archive-listed): harvested for 4 other papers, listed under the repository
- jacobgil/vit-explain, community (archive-listed): harvested for 2 other papers, listed under the repository
- nus-hpc-ai-lab/dyvm, community (archive-listed): harvested for another paper, listed under the repository
- s-chh/patchrot, community (archive-listed): harvested for another paper, listed under the repository
- skchen1993/TrangFG, community (archive-listed): harvested for another paper, listed under the repository
- smu-ivpl/DeepfakeDetection, community (archive-listed): harvested for 2 other papers, listed under the repository
- tianhai123/vit-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- ttt496/vit-pytorch, community (archive-listed): harvested for 3 other papers, listed under the repository
- wangyz1608/knowledge-distillation-via-nd, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PLSC, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
40 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
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.
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.
c1c79ef7fd065038 · report
fixture: signature features:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22 4eae8cfd26a7bed5 · report
fee0f891e0558ff8 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 b42ba639d4f94082 · report
fixture: returned DistillationLoss · level recorded 2026-09-22 e089d779e4638b42 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 295ab55989f9e8fe · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22 9e38671b1e2518ec · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22 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 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 64505a0b6aa5e3d4 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 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 c4a17f13fadc2630 · report
fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float · returned Tensor · level recorded 2026-09-24 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 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket easycv/models/backbones/vision_transformer.py unverified Apache-2.0 (permissive) ·
bc7c311c2770067a · report
c152c68202903a9f · report
a4ea24ce126312f8 · report
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
- 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
- _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
- 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
- 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
- DeiT entry · level 0 · unverified ·
4eae8cfd26a7bed5 - VisionEncoder model · level 1 · ran ·
bacfe561400c3879 - 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
- 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
- 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
- VisionTransformer entry · level 0 · unverified ·
a4ea24ce126312f8 - Block model · level 0 · unverified ·
bc7c311c2770067a - PatchEmbed model · level 1 · ran ·
9187f42531072c00 - ValueError helper · level 0 · unverified ·
c152c68202903a9f - trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) ·
462cf9fa4898bc51 - Attention model · level 1 · ran ·
c0bfabc05e380222 - DropPath helper · level 1 · ran ·
c713760d26bf0a45 - Mlp helper · level 1 · ran ·
64505a0b6aa5e3d4 - drop_path helper · level 1 · ran; the contract check could not run ·
55120f2026b56aa2 - BaseError helper · level 1 · ran ·
6f3e4e43ff039081 - _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) ·
5bcbd988b672cf32 - hydra helper · level 1 · ran · our draft was wrong ·
c4a17f13fadc2630 - KeyError helper · level 1 · ran ·
cd97bea208feabb0 - Registry helper · level 0 · unverified ·
c0e3084b8e16dcc1 - 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
- DepthwiseViT entry · level 0 · unverified ·
fa8c4e7bc2b8d354 - TransformerEncoder model · level 1 · ran ·
9e38671b1e2518ec - 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
Results from the paper archive 2025-07-28
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
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