Papers › MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

5 Oct 2021ICLR 2022 4arXiv:2110.02178archive 2025-07-28

Sachin Mehta, Mohammad Rastegari

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are spatially local. To learn global representations, self-attention-based vision trans-formers (ViTs) have been adopted. Unlike CNNs, ViTs are heavy-weight. In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks? Towards this end, we introduce MobileViT, a light-weight and general-purpose vision transformer for mobile devices. MobileViT presents a different perspective for the global processing of information with transformers, i.e., transformers as convolutions. Our results show that MobileViT significantly outperforms CNN- and ViT-based networks across different tasks and datasets. On the ImageNet-1k dataset, MobileViT achieves top-1 accuracy of 78.4% with about 6 million parameters, which is 3.2% and 6.2% more accurate than MobileNetv3 (CNN-based) and DeIT (ViT-based) for a similar number of parameters. On the MS-COCO object detection task, MobileViT is 5.7% more accurate than MobileNetv3 for a similar number of parameters. Our source code is open-source and available at: https://github.com/apple/ml-cvnets

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

The archive's official repository (apple/ml-cvnets) was not harvested; the 67 samples below come from 9 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 68 code samples: 67 from 9 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 68: 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 67 samples from 9 repositories, 52 ran (44 with no instrument failure; 8 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 9 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. 2 of the 53 samples that ran have no recorded date.

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

apple/ml-cvnets officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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
chinhsuanwu/mobilevit-pytorch mentioned on GitHubpytorchSyntology: 10 samples, 7 ran (2 instrument-failed) · 3 unverified report
godhj93/MobileViT mentioned on GitHubtfSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
hkzhang91/edgeformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer (arXiv:2203.03952; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hkzhang91/pacc-net mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer (arXiv:2203.03952; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hkzhang91/parc-net mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer (arXiv:2203.03952; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jaiwei98/mobile-vit-pytorch mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (1 instrument-failed) · 1 unverified report
james77777778/keras-image-models mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GhostNetV3: Exploring the Training Strategies for Compact Models (arXiv:2404.11202; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
microndla/mobilevitv3 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
mmaaz60/EdgeNeXt mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
murufeng/awesome_lightweight_networks mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (1 instrument-failed) · 1 unverified report
roydenwa/cell-centroid-former mentioned on GitHubtfSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
rwightman/pytorch-image-models mentioned 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
t0nyliang/EEGMobile mentioned on GitHubpytorchSyntology: not harvested report
wilile26811249/MobileViT mentioned on GitHubpytorchSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
xmu-xiaoma666/External-Attention-pytorch mentioned on GitHubpytorchSyntology: 8 samples, 7 ran (1 instrument-failed) · 1 unverified report
BR-IDL/PaddleViT paddleSyntology: not harvested report
Mind23-2/MindCode-103 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code400 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
avinash31d/paper-implementations tfApache-2.0Syntology: not harvested report
kornia/kornia pytorchSyntology: 9 samples, 7 ran (2 instrument-failed) · 2 unverified report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
open-mmlab/mmclassification pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-5 mindsporeSyntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/MobileViT mindsporeSyntology: 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

68 samples harvested: 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 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
9ran · our draft was wrong
43ran
15unverified

Licence: 18 of the 68 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. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 20 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.

chinhsuanwu/mobilevit-pytorch community (archive-listed) 10 samples, 7 ran (2 instrument-failed) · 3 unverified
FeedForward in 198 papers mobilevit.py ran · metamorphic tier: invariant MIT (permissive) · 58080bbc3d99ba0f · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MV2Block mobilevit.py ran · metamorphic tier: invariant MIT (permissive) · d8b589747023f0ed · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MobileViTBlock mobilevit.py ran MIT (permissive) · 8eca4842b31caba0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Transformer in 173 papers mobilevit.py ran · metamorphic tier: invariant MIT (permissive) · 09bb5fbbbccebe6b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
conv_1x1_bn in 59 papers mobilevit.py ran · our draft was wrong MIT (permissive) · 3fb34464dacbb0d3 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_nxn_bn mobilevit.py ran · our draft was wrong MIT (permissive) · e01bc963fa545868 · report fixture: signature inp:int/0/int, oup:int/0/int, kernal_size:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
count_parameters in 278 papers mobilevit.py ran · honoured contract MIT (permissive) · 3d1cb4db0a0a03e9 · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
MobileViT mobilevit.py unverified MIT (permissive) · d8f1a24b68aa0b29 · report
conv_1x1_bn in 59 papers mobilevit.py unverified MIT (permissive) · 248f0c82db73b84d · report
conv_nxn_bn mobilevit.py unverified MIT (permissive) · ba426aae4d6a9c16 · report
godhj93/MobileViT community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
EncoderLayer in 73 papers utils/nets/MobileViT.py ran no licence file found · pointer only · 20ec52f2f7242b3d · report fixture: returned EncoderLayer · level recorded 2026-09-22
MViT_block utils/nets/MobileViT.py ran no licence file found · pointer only · 0d8adae319bee6c7 · report fixture: returned MViT_block · level recorded 2026-09-22
extract_patches in 34 papers utils/nets/MobileViT.py ran no licence file found · pointer only · f4179768dbc55e61 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
patches_to_image utils/nets/MobileViT.py ran no licence file found · pointer only · fa37ccabf8400bc6 · report fixture: returned patches_to_image · level recorded 2026-09-22
InvertedResidual in 9 papers utils/nets/MobileViT.py unverified no licence file found · pointer only · 6e05718496381a26 · report
MobileViT utils/nets/MobileViT.py unverified no licence file found · pointer only · 86afc1196b6b0ee1 · report
jaiwei98/mobile-vit-pytorch community (archive-listed) 6 samples, 5 ran (1 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
mobile_vit/mobilevit.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7dce48772b2e159a · report fixture: returned Attention · level recorded 2026-09-22
InvertedResidual in 9 papers mobile_vit/mobilevit.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · c56c074407924b8b · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileViTBlock mobile_vit/mobilevit.py ran · metamorphic tier: deterministic no licence file found · pointer only · 51b0a869e04e4c79 · report fixture: returned MobileViTBlock · level recorded 2026-09-22
TransformerEncoder in 96 papers mobile_vit/mobilevit.py ran · metamorphic tier: deterministic no licence file found · pointer only · bd36e71d0ee3fd10 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
conv_2d in 7 papers mobile_vit/mobilevit.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 · our draft was wrong licence of this copy not recorded · 46467acb70052484 · report fixture: signature inp:int/0/int, oup:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, groups:int/0/int, bias:bool/0/bool, norm:bool/0/bool, act:bool/0/bool · returned Sequential · level recorded, date not recorded
MobileViT mobile_vit/mobilevit.py unverified no licence file found · pointer only · 9758df99f0486f48 · report
mmaaz60/EdgeNeXt community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
ConvEncoder in 12 papers models/edgenext.py ran · metamorphic tier: deterministic MIT (permissive) · a75100d19286cb15 · report fixture: returned ConvEncoder · 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
models/edgenext.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d59faa990dd0baa0 · report fixture: returned LayerNorm · level recorded 2026-09-22
PositionalEncodingFourier models/edgenext.py ran · metamorphic tier: deterministic MIT (permissive) · 9917b766bd4dba3a · report fixture: returned PositionalEncodingFourier · level recorded 2026-09-22
SDTAEncoder models/edgenext.py ran · metamorphic tier: deterministic MIT (permissive) · 7e438b1b13e38d9d · report fixture: returned SDTAEncoder · level recorded 2026-09-22
XCA models/edgenext.py ran · metamorphic tier: deterministic MIT (permissive) · 2733c35c71b87333 · report fixture: returned XCA · level recorded 2026-09-22
EdgeNeXt models/edgenext.py unverified MIT (permissive) · d8d7e7e34dc91a1e · report
murufeng/awesome_lightweight_networks community (archive-listed) 7 samples, 6 ran (1 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
light_cnns/Transformer/mobile_vit.py ran · metamorphic tier: invariant MIT (permissive) · 43531c7c47f675ef · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Conv_BN_ReLU light_cnns/Transformer/mobile_vit.py ran · our draft was wrong MIT (permissive) · 38ab7af20618ac3e · report fixture: signature inp:int/0/int, oup:int/0/int, kernel:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
FeedForward in 198 papers light_cnns/Transformer/mobile_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 4d1e816536427160 · report fixture: returned FeedForward · level recorded 2026-09-22
MV2Block light_cnns/Transformer/mobile_vit.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · e789209b847f99a6 · report fixture: returned MV2Block · level recorded 2026-09-22
MobileViTBlock light_cnns/Transformer/mobile_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 69a7b757b4410e76 · report fixture: returned MobileViTBlock · level recorded 2026-09-22
Transformer in 173 papers light_cnns/Transformer/mobile_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 127b3963437b49e3 · report fixture: returned Transformer · level recorded 2026-09-22
MobileViT light_cnns/Transformer/mobile_vit.py unverified MIT (permissive) · 773215bd26648b60 · report
roydenwa/cell-centroid-former community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
ChannelMLP src/cellcentroidformer/model_architecture.py ran no licence file found · pointer only · f1f1c5ff227fe41d · report fixture: returned ChannelMLP · level recorded 2026-09-22
MobileViTBlock src/cellcentroidformer/model_architecture.py ran no licence file found · pointer only · 6f15cb3df6e1d23e · report fixture: returned MobileViTBlock · level recorded 2026-09-22
MultiLayerPerceptron in 6 papers src/cellcentroidformer/model_architecture.py ran no licence file found · pointer only · c6e2b5d57c742ded · report fixture: returned MultiLayerPerceptron · level recorded 2026-09-22
TransformerEncoder in 96 papers src/cellcentroidformer/model_architecture.py ran no licence file found · pointer only · 50c31c18f8304002 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
compact_get_layers src/cellcentroidformer/model_architecture.py ran · our draft was wrong no licence file found · pointer only · cf5208ed947ab445 · report fixture: signature module:SimpleModule/0/? · returned SimpleModule · level recorded 2026-09-22
wilile26811249/MobileViT community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
ConvNormAct models/model.py ran fingerprinted MIT (permissive) · 8ed7073f6f37a1a1 · report fixture: returned ConvNormAct · level recorded 2026-09-22
FFN in 37 papers models/model.py ran MIT (permissive) · 0700a6a34626a6bf · report fixture: returned FFN · level recorded 2026-09-22
InvertedResidual in 9 papers models/model.py ran fingerprinted MIT (permissive) · cc6fad7bef0b8c04 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileVitBlock models/model.py ran MIT (permissive) · 355dd4ca53ea56d8 · report fixture: returned MobileVitBlock · level recorded 2026-09-22
MultiHeadSelfAttention in 17 papers models/model.py ran MIT (permissive) · 3b57311302acf06c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Transformer in 173 papers models/model.py ran MIT (permissive) · 54a5e3106186035e · report fixture: returned Transformer · level recorded 2026-09-22
MobileViT models/model.py unverified MIT (permissive) · 36d81e4406f2c1da · report
MobileViT_S models/model.py unverified MIT (permissive) · ed15506c976a883e · report
MobileViT_XS models/model.py unverified MIT (permissive) · ccdc152785a294d2 · report
MobileViT_XXS models/model.py unverified MIT (permissive) · 6014219e7ea97f79 · report
xmu-xiaoma666/External-Attention-pytorch community (archive-listed) 8 samples, 7 ran (1 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model/backbone/MobileViT.py ran · metamorphic tier: deterministic MIT (permissive) · d55210e5cfb23cea · report fixture: returned Attention · level recorded 2026-09-22
FeedForward in 198 papers model/backbone/MobileViT.py ran · metamorphic tier: deterministic MIT (permissive) · 878fe3f52adf2d34 · report fixture: returned FeedForward · level recorded 2026-09-22
MV2Block model/backbone/MobileViT.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7a5ed61c85d652d3 · report fixture: returned MV2Block · level recorded 2026-09-22
MobileViTAttention model/backbone/MobileViT.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 315d52a69ddead31 · report fixture: returned MobileViTAttention · level recorded 2026-09-22
PreNorm in 34 papers model/backbone/MobileViT.py ran · metamorphic tier: deterministic MIT (permissive) · bcbab17e442a74cb · report fixture: returned PreNorm · level recorded 2026-09-22
Transformer in 173 papers model/backbone/MobileViT.py ran · metamorphic tier: deterministic MIT (permissive) · 8ae59a8594d1df08 · report fixture: returned Transformer · level recorded 2026-09-22
conv_bn in 88 papers model/backbone/MobileViT.py ran · our draft was wrong MIT (permissive) · 3fc0fa5c567d1a28 · report fixture: returned Sequential · level recorded 2026-09-22
MobileViT model/backbone/MobileViT.py unverified MIT (permissive) · aee9977341677a30 · report
kornia/kornia community (archive-listed) 9 samples, 7 ran (2 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
kornia/models/vit_mobile.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 2230f658d6c25822 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
FeedForward in 198 papers kornia/models/vit_mobile.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 144b7a438af242ef · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MV2Block kornia/models/vit_mobile.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · ed0efa372d4badcc · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
PreNorm in 34 papers kornia/models/vit_mobile.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 4bdddb9b8d76e1b6 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers kornia/models/vit_mobile.py ran Apache-2.0 (permissive) · 56bdd39960d3695b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
conv_1x1_bn in 59 papers kornia/models/vit_mobile.py ran · our draft was wrong Apache-2.0 (permissive) · 564f22f3b28db627 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_nxn_bn kornia/models/vit_mobile.py ran · our draft was wrong Apache-2.0 (permissive) · 8d5317047e54ef09 · report fixture: signature inp:int/0/int, oup:int/0/int, kernal_size:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
MobileViT kornia/models/vit_mobile.py unverified Apache-2.0 (permissive) · 1ac664c178170ffe · report
MobileViTBlock kornia/models/vit_mobile.py unverified Apache-2.0 (permissive) · 8be19ea313e7777e · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv_1x1_bn in 59 papers repository not located ran · our draft was wrong licence of this copy not recorded · a0131fb70c267a9e · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · 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.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for MobileViT (graph method: MobileViT). 6 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · 86afc1196b6b0ee1
  2. InvertedResidual model · level 0 · unverified · 6e05718496381a26
  3. MViT_block model · level 1 · ran · 0d8adae319bee6c7
  4. EncoderLayer helper · level 1 · ran · 20ec52f2f7242b3d
  5. extract_patches helper · level 1 · ran · f4179768dbc55e61
  6. patches_to_image helper · level 1 · ran · fa37ccabf8400bc6

harvested Assembly for MobileViT (graph method: MobileViT). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · 9758df99f0486f48
  2. InvertedResidual model · level 1 · ran · c56c074407924b8b
  3. MobileViTBlock model · level 1 · ran · 51b0a869e04e4c79
  4. conv_2d helper · level 1 · ran · our draft was wrong · 46467acb70052484
  5. TransformerEncoder model · level 1 · ran · bd36e71d0ee3fd10
  6. Attention model · level 1 · ran · 7dce48772b2e159a

harvested Assembly for MobileViT (graph method: MobileViT). 5 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViTBlock entry · level 1 · ran · 6f15cb3df6e1d23e
  2. TransformerEncoder helper · level 1 · ran · 50c31c18f8304002
  3. compact_get_layers helper · level 1 · ran · our draft was wrong · cf5208ed947ab445
  4. ChannelMLP helper · level 1 · ran · f1f1c5ff227fe41d
  5. MultiLayerPerceptron helper · level 1 · ran · c6e2b5d57c742ded

harvested Assembly for MobileViT (graph method: MobileViT). 9 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · 773215bd26648b60
  2. Conv_BN_ReLU helper · level 1 · ran · our draft was wrong · 38ab7af20618ac3e
  3. MV2Block model · level 1 · ran · e789209b847f99a6
  4. MobileViTBlock model · level 1 · ran · 69a7b757b4410e76
  5. conv_1x1_bn helper · level 1 · ran · our draft was wrong · a0131fb70c267a9e
  6. Transformer model · level 1 · ran · 127b3963437b49e3
  7. Attention model · level 1 · ran · 43531c7c47f675ef
  8. FeedForward model · level 1 · ran · 4d1e816536427160
  9. PreNorm helper · level 1 · ran · 9b66b60a7704b891

harvested Assembly for MobileViT (graph method: MobileViT). 8 bricks; individually on a fixture: 7 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · aee9977341677a30
  2. MV2Block model · level 1 · ran · 7a5ed61c85d652d3
  3. MobileViTAttention model · level 1 · ran · 315d52a69ddead31
  4. conv_bn helper · level 1 · ran · our draft was wrong · 3fc0fa5c567d1a28
  5. Transformer model · level 1 · ran · 8ae59a8594d1df08
  6. Attention helper · level 1 · ran · d55210e5cfb23cea
  7. FeedForward helper · level 1 · ran · 878fe3f52adf2d34
  8. PreNorm helper · level 1 · ran · bcbab17e442a74cb

harvested Assembly for MobileViT (graph method: MobileViT). 8 bricks; individually on a fixture: 7 ran (of which 6 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. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · 36d81e4406f2c1da
  2. InvertedResidual model · level 1 · ran · cc6fad7bef0b8c04
  3. MobileVitBlock model · level 1 · ran · 355dd4ca53ea56d8
  4. ConvNormAct helper · level 1 · ran · 8ed7073f6f37a1a1
  5. Transformer model · level 1 · ran · 54a5e3106186035e
  6. FFN model · level 1 · ran · 0700a6a34626a6bf
  7. MultiHeadSelfAttention model · level 1 · ran · 3b57311302acf06c
  8. PreNorm helper · level 1 · ran · 9b66b60a7704b891

harvested Assembly for MobileViT (graph method: MobileViT). 9 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · d8f1a24b68aa0b29
  2. MV2Block model · level 1 · ran · d8b589747023f0ed
  3. MobileViTBlock model · level 1 · ran · 8eca4842b31caba0
  4. conv_1x1_bn helper · level 1 · ran · our draft was wrong · 3fb34464dacbb0d3
  5. conv_nxn_bn helper · level 1 · ran · our draft was wrong · e01bc963fa545868
  6. Transformer model · level 1 · ran · 09bb5fbbbccebe6b
  7. Attention model · level 1 · ran · 43531c7c47f675ef
  8. FeedForward model · level 1 · ran · 58080bbc3d99ba0f
  9. PreNorm helper · level 1 · ran · 9b66b60a7704b891

harvested Assembly for MobileViT (graph method: MobileViT). 9 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. MobileViT entry · level 0 · unverified · 1ac664c178170ffe
  2. MV2Block model · level 1 · ran · ed0efa372d4badcc
  3. MobileViTBlock model · level 0 · unverified · 8be19ea313e7777e
  4. conv_1x1_bn helper · level 1 · ran · our draft was wrong · 564f22f3b28db627
  5. conv_nxn_bn helper · level 1 · ran · our draft was wrong · 8d5317047e54ef09
  6. Transformer model · level 1 · ran · 56bdd39960d3695b
  7. Attention model · level 1 · ran · 2230f658d6c25822
  8. FeedForward model · level 1 · ran · 144b7a438af242ef
  9. PreNorm helper · level 1 · ran · 4bdddb9b8d76e1b6

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="2110.02178") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MobileViT-S Number of params 5.6M #837 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViT-S Top 1 Accuracy 78.4% #837 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViT-XS GFLOPs 0.7 #968 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViT-XS Number of params 2.3M #968 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViT-XS Top 1 Accuracy 74.8% #968 of 1060 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: MobileViT

1x1 ConvolutionAttentionAttention DropoutAverage PoolingBatch NormalizationConvolutionDeiTDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutFeedforward NetworkGlobal Average PoolingHard SwishInverted Residual BlockLayer NormalizationLinear LayerMobileViTMulti-Head AttentionPointwise ConvolutionReLUReLU6Residual ConnectionSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockVision 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