Papers › CvT: Introducing Convolutions to Vision Transformers

CvT: Introducing Convolutions to Vision Transformers

29 Mar 2021ICCV 2021 10arXiv:2103.15808archive 2025-07-28

Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang

We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is accomplished through two primary modifications: a hierarchy of Transformers containing a new convolutional token embedding, and a convolutional Transformer block leveraging a convolutional projection. These changes introduce desirable properties of convolutional neural networks (CNNs) to the ViT architecture (i.e. shift, scale, and distortion invariance) while maintaining the merits of Transformers (i.e. dynamic attention, global context, and better generalization). We validate CvT by conducting extensive experiments, showing that this approach achieves state-of-the-art performance over other Vision Transformers and ResNets on ImageNet-1k, with fewer parameters and lower FLOPs. In addition, performance gains are maintained when pretrained on larger datasets (e.g. ImageNet-22k) and fine-tuned to downstream tasks. Pre-trained on ImageNet-22k, our CvT-W24 obtains a top-1 accuracy of 87.7% on the ImageNet-1k val set. Finally, our results show that the positional encoding, a crucial component in existing Vision Transformers, can be safely removed in our model, simplifying the design for higher resolution vision tasks. Code will be released at https://github.com/leoxiaobin/CvT.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 47 code samples: 45 from 7 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 47: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed); named in the paper: 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 29 samples from 5 repositories, 25 ran (25 with no instrument failure; 0 where Syntology's instrument failed); 2 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 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 39 samples that ran have no recorded date.

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

microsoft/CvT officialmentioned on GitHubpytorchMITSyntology: 14 samples, 10 ran (0 instrument-failed) · 4 unverified report
leoxiaobin/CvT mentioned in papermentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
BR-IDL/PaddleViT mentioned on GitHubpaddleApache-2.0Syntology: not harvested report
EMalagoli92/CvT-TensorFlow mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
SforAiDl/vformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vision Transformers for Dense Prediction (arXiv:2103.13413; that paper's own run record: 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified) and ViViT: A Video Vision Transformer (arXiv:2103.15691; that paper's own run record: 14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
ZackPashkin/CvT-convolutional-transformer-pytorch mentioned on GitHubpytorchSyntology: not harvested report
ahmedelmahy/myownvit mentioned on GitHubpytorchSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
conceptofmind/CvT-flax mentioned on GitHubjaxSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 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
rishikksh20/convolution-vision-transformers mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified 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
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Oguzhanercan/Vision-Transformers Syntology: not harvested report
PaddlePaddle/PASSL paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
microsoft/esvit pytorchSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified 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

47 samples harvested: 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. “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.

2ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
34ran
8unverified

Licence: 8 of the 47 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 7 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. 2 samples are 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.

microsoft/CvT official repository 14 samples, 10 ran (0 instrument-failed) · 4 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
lib/core/evaluate.py ran MIT (permissive) · 48af950e22ac823c · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
all_gather in 119 papers lib/utils/comm.py ran MIT (permissive) · dbb4a0fbb6f9600c · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-25
build_criterion lib/core/loss.py ran MIT (permissive) · 79e00b7e79094bff · report fixture: signature config:Config/0/?, train:bool/0/bool · returned LabelSmoothingCrossEntropy · level recorded 2026-09-25
build_model in 469 papers lib/models/build.py ran MIT (permissive) · 0f4931981bc034df · report fixture: returned DummyModel · level recorded 2026-09-25
build_optimizer in 83 papers lib/optim/build.py ran MIT (permissive) · cafe3a0bb0d90db6 · report fixture: signature cfg:Config/0/?, model:callable/0/? · returned AdamW · level recorded 2026-09-25
count_parameters in 278 papers lib/utils/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 6a41f5e3194a54b1 · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-24
is_model in 24 papers lib/models/registry.py ran MIT (permissive) here; the stored copy is pointer only · 86c6e09f9f6f6637 · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-24
reduce_dict in 73 papers lib/utils/comm.py ran MIT (permissive) · 19a8d1208f8a920f · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-25
register_model in 68 papers lib/models/registry.py ran MIT (permissive) here; the stored copy is pointer only · be2fbb8bf98a15f7 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
set_wd lib/optim/build.py ran MIT (permissive) · 210dd79dd3fdc950 · report fixture: signature cfg:Config/0/?, model:callable/0/? · returned list · level recorded 2026-09-25
build_dataloader in 19 papers lib/dataset/build.py unverified MIT (permissive) · 51dc0ff05a226bd7 · report
build_dataset in 151 papers lib/dataset/build.py unverified MIT (permissive) · d664b0a074d4c567 · report
build_lr_scheduler in 13 papers lib/scheduler/build.py unverified MIT (permissive) · 60eb73feb15fe78a · report
model_entrypoints lib/models/registry.py unverified MIT (permissive) here; the stored copy is pointer only · 0c3902b80e9968b5 · report
leoxiaobin/CvT named in the paper 2 samples, 2 ran (1 instrument-failed) · 0 unverified
linear_combination lib/core/loss.py ran · honoured contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · ee5e85cfd16bc5dc · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, epsilon:float/0/float · returned Tensor · level recorded, date not recorded
reduce_loss in 75 papers lib/core/loss.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT recorded; this copy not marked cleared · pointer only · 9f7b947fbfdaa657 · report fixture: signature loss:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded, date not recorded
EMalagoli92/CvT-TensorFlow community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
norm_cdf in 8 papers cvt_tensorflow/models/layers/utils.py ran fingerprinted MIT (permissive) · 1e7a21b70e475e05 · report fixture: signature x:float/0/float · returned float · level recorded 2026-09-25
run_layers_list cvt_tensorflow/models/utils.py ran MIT (permissive) · 8db082cfc9d2e2cf · report fixture: signature input_:EagerTensor/2/float, list_:list/1/callable · returned EagerTensor · level recorded 2026-09-24
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
cvt_tensorflow/models/layers/utils.py ran MIT (permissive) · 1ad1d109f5a6e55b · report fixture: signature shape:tuple/1/int, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-24
ahmedelmahy/myownvit community (archive-listed) 7 samples, 7 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
vit_pytorch/cvt.py ran · metamorphic tier: deterministic MIT (permissive) · 991c37c831796a95 · report fixture: returned Attention · level recorded 2026-09-22
CvT vit_pytorch/cvt.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a834f7b8ea0f91fd · report fixture: returned CvT · level recorded 2026-09-22
DepthWiseConv2d vit_pytorch/cvt.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 28e2a060ad0a121a · report fixture: returned DepthWiseConv2d · level recorded 2026-09-22
FeedForward in 198 papers vit_pytorch/cvt.py ran · metamorphic tier: deterministic MIT (permissive) · 4c414437e8099db9 · report fixture: returned FeedForward · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
vit_pytorch/cvt.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f919bd05baa8dbfe · report fixture: returned LayerNorm · level recorded 2026-09-22
PreNorm in 34 papers vit_pytorch/cvt.py ran · metamorphic tier: deterministic MIT (permissive) · ada83fa4cdf0ade2 · report fixture: returned PreNorm · level recorded 2026-09-22
Transformer in 173 papers vit_pytorch/cvt.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 85fb09fd1d03038f · report fixture: returned Transformer · level recorded 2026-09-22
conceptofmind/CvT-flax community (archive-listed) 7 samples, 6 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
cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · 52559df32e30ffb2 · report fixture: returned Attention · level recorded 2026-09-22
CvT cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · 6fd86ebfed8c45ff · report fixture: returned CvT · level recorded 2026-09-22
DepthWiseConv2d cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · d3ffd9a7becc875f · report fixture: returned DepthWiseConv2d · level recorded 2026-09-22
FeedForward in 198 papers cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · a4ee1f00f5b87c00 · report fixture: returned FeedForward · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · 9822786697807511 · report fixture: returned LayerNorm · level recorded 2026-09-22
Transformer in 173 papers cvt_flax/cvt_flax.py ran · metamorphic tier: deterministic MIT (permissive) · 0a5b9eec36824115 · report fixture: returned Transformer · level recorded 2026-09-22
GlobalAvgPool cvt_flax/cvt_flax.py unverified MIT (permissive) · 36c58f137e9289c0 · report
rishikksh20/convolution-vision-transformers community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
ConvAttention cvt.py ran · metamorphic tier: invariant MIT (permissive) · 24f6586f5de31374 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
SepConv2d cvt.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 9cc172a07a92afb4 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers cvt.py ran MIT (permissive) · d6576534c1091ccc · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
CvT cvt.py unverified MIT (permissive) · 9d4228c318890e3e · report
microsoft/esvit community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/cvt_v4_transformer.py ran MIT (permissive) · 28bc4fb247eda528 · report fixture: returned Attention · level recorded 2026-09-22
ConvEmbed models/cvt_v4_transformer.py ran fingerprinted MIT (permissive) · ae1afcb4cbd9e8a8 · report fixture: returned ConvEmbed · level recorded 2026-09-22
DepthWiseConv2d models/cvt_v4_transformer.py ran fingerprinted MIT (permissive) · 1900dc0d402d75ab · report fixture: returned DepthWiseConv2d · level recorded 2026-09-22
FeedForward in 198 papers models/cvt_v4_transformer.py ran MIT (permissive) · a4becc1ab3fb3cb3 · report fixture: returned FeedForward · level recorded 2026-09-22
PreNorm in 34 papers models/cvt_v4_transformer.py ran MIT (permissive) · c296102b024e1211 · report fixture: returned PreNorm · level recorded 2026-09-22
ResStem models/cvt_v4_transformer.py ran fingerprinted MIT (permissive) · 72cd0feff4d8e28f · report fixture: returned ResStem · level recorded 2026-09-22
CvT models/cvt_v4_transformer.py unverified MIT (permissive) · addb189889d498a2 · report
Transformer in 173 papers models/cvt_v4_transformer.py unverified MIT (permissive) · 00dced1853563caf · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are 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.
group_by_key_prefix_and_remove_prefix repository not located ran · our draft was wrong licence of this copy not recorded · ca4faa49da53bd5c · report fixture: signature prefix:str/0/str, d:dict/0/? · returned tuple · level recorded 2026-09-22
group_dict_by_key repository not located ran · our draft was wrong licence of this copy not recorded · afcf8f2954675d55 · report fixture: signature cond:callable/0/?, d:dict/0/? · returned tuple · level recorded 2026-09-22

Method as code Syntology

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

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

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

harvested Assembly for CvT (graph method: CvT). 9 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. CvT entry · level 1 · ran · a834f7b8ea0f91fd
  2. LayerNorm helper · level 1 · ran · f919bd05baa8dbfe
  3. Transformer model · level 1 · ran · 85fb09fd1d03038f
  4. group_by_key_prefix_and_remove_prefix helper · level 1 · ran · our draft was wrong · ca4faa49da53bd5c
  5. Attention model · level 1 · ran · 991c37c831796a95
  6. FeedForward model · level 1 · ran · 4c414437e8099db9
  7. PreNorm helper · level 1 · ran · ada83fa4cdf0ade2
  8. group_dict_by_key helper · level 1 · ran · our draft was wrong · afcf8f2954675d55
  9. DepthWiseConv2d model · level 1 · ran · 28e2a060ad0a121a

harvested Assembly for CvT (graph method: CvT). 8 bricks; individually on a fixture: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 7 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. CvT entry · level 1 · ran · 6fd86ebfed8c45ff
  2. GlobalAvgPool helper · level 0 · unverified · 36c58f137e9289c0
  3. LayerNorm helper · level 1 · ran · 9822786697807511
  4. Transformer model · level 1 · ran · 0a5b9eec36824115
  5. Attention model · level 1 · ran · 52559df32e30ffb2
  6. FeedForward model · level 1 · ran · a4ee1f00f5b87c00
  7. PreNorm helper · level 1 · ran · 4cf5ff951dbba496
  8. DepthWiseConv2d model · level 1 · ran · d3ffd9a7becc875f

harvested Assembly for CvT (graph method: CvT). 8 bricks; individually on a fixture: 6 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; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. CvT entry · level 0 · unverified · addb189889d498a2
  2. ConvEmbed model · level 1 · ran · ae1afcb4cbd9e8a8
  3. ResStem model · level 1 · ran · 72cd0feff4d8e28f
  4. Transformer model · level 0 · unverified · 00dced1853563caf
  5. Attention model · level 1 · ran · 28bc4fb247eda528
  6. FeedForward model · level 1 · ran · a4becc1ab3fb3cb3
  7. PreNorm helper · level 1 · ran · c296102b024e1211
  8. DepthWiseConv2d model · level 1 · ran · 1900dc0d402d75ab

harvested Assembly for CvT (graph method: CvT). 6 bricks; individually on a fixture: 5 ran (of which 2 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. The assembly has not been run end-to-end.

one of 4 siblings

  1. CvT entry · level 0 · unverified · 9d4228c318890e3e
  2. Transformer model · level 1 · ran · d6576534c1091ccc
  3. ConvAttention helper · level 1 · ran · 24f6586f5de31374
  4. FeedForward helper · level 1 · ran · c17d96c99b861de1
  5. PreNorm helper · level 1 · ran · 005532cda6b215dd
  6. SepConv2d helper · level 1 · ran · 9cc172a07a92afb4

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="2103.15808") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 CvT-W24 Percentage correct 99.39 #6 of 265 Archive leaderboard report
Image Classification CIFAR-100 CvT-W24 Percentage correct 94.09 #5 of 211 Archive leaderboard report
Image Classification Flowers-102 CvT-W24 Accuracy 99.72 #3 of 52 Archive leaderboard report
Image Classification ImageNet CvT-W24 (384 res, ImageNet-22k pretrain) Top 1 Accuracy 87.7% #76 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 (384 res, ImageNet-22k pretrain) GFLOPs 25 #279 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 (384 res, ImageNet-22k pretrain) Number of params 32M #279 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 (384 res, ImageNet-22k pretrain) Top 1 Accuracy 84.9% #279 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 (384 res) GFLOPs 24.9 #435 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 (384 res) Top 1 Accuracy 83.3% #435 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13 (384 res) GFLOPs 16.3 #476 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13 (384 res) Number of params 20M #476 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13 (384 res) Top 1 Accuracy 83% #476 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 GFLOPs 7.1 #527 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-21 Top 1 Accuracy 82.5% #527 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13-NAS GFLOPs 4.1 #560 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13-NAS Number of params 18M #560 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13-NAS Top 1 Accuracy 82.2% #560 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13 GFLOPs 4.5 #620 of 1060 Archive leaderboard report
Image Classification ImageNet CvT-13 Top 1 Accuracy 81.6% #620 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL CvT-W24 (384 res, ImageNet-22k pretrain) Accuracy 90.6% #14 of 57 Archive leaderboard report
Image Classification ImageNet ReaL CvT-W24 (384 res, ImageNet-22k pretrain) Number of params 277M #14 of 57 Archive leaderboard report
Image Classification ImageNet ReaL CvT-W24 (384 res, ImageNet-22k pretrain) Top 1 Accuracy 87.7% #14 of 57 Archive leaderboard report
Image Classification Oxford-IIIT Pets CvT-W24 Accuracy 94.73 #2 of 6 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: CvT

Absolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationConvolutionCvTDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPointwise ConvolutionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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