Papers › MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
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
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2110.02178")
Code
Syntology Ran 53 of 68 code samples harvested from 9 repositories linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · honoured contract; 9 ran · our draft was wrong; 43 ran with no contract checked.
By repository: community (archive-listed): 66 samples from 9 repositories, 51 ran; 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.
31 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.
Code Syntology ran Syntology
68 samples harvested; 53 ran; 1 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
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; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.
7dce48772b2e159a · report
43531c7c47f675ef · report
d55210e5cfb23cea · report
2230f658d6c25822 · report
f1f1c5ff227fe41d · report
a75100d19286cb15 · report
8ed7073f6f37a1a1 · report
38ab7af20618ac3e · report
20ec52f2f7242b3d · report
0700a6a34626a6bf · report
4d1e816536427160 · report
878fe3f52adf2d34 · report
58080bbc3d99ba0f · report
144b7a438af242ef · report
c56c074407924b8b · report
cc6fad7bef0b8c04 · report
d59faa990dd0baa0 · report
e789209b847f99a6 · report
7a5ed61c85d652d3 · report
d8b589747023f0ed · report
ed0efa372d4badcc · report
0d8adae319bee6c7 · report
315d52a69ddead31 · report
51b0a869e04e4c79 · report
6f15cb3df6e1d23e · report
69a7b757b4410e76 · report
8eca4842b31caba0 · report
355dd4ca53ea56d8 · report
3b57311302acf06c · report
c6e2b5d57c742ded · report
9917b766bd4dba3a · report
bcbab17e442a74cb · report
4bdddb9b8d76e1b6 · report
7e438b1b13e38d9d · report
127b3963437b49e3 · report
8ae59a8594d1df08 · report
54a5e3106186035e · report
09bb5fbbbccebe6b · report
56bdd39960d3695b · report
bd36e71d0ee3fd10 · report
50c31c18f8304002 · report
2733c35c71b87333 · report
cf5208ed947ab445 · report
3fb34464dacbb0d3 · report
564f22f3b28db627 · report
3fc0fa5c567d1a28 · report
e01bc963fa545868 · report
8d5317047e54ef09 · report
3d1cb4db0a0a03e9 · report
f4179768dbc55e61 · report
fa37ccabf8400bc6 · report
d8d7e7e34dc91a1e · report
6e05718496381a26 · report
86afc1196b6b0ee1 · report
9758df99f0486f48 · report
773215bd26648b60 · report
aee9977341677a30 · report
36d81e4406f2c1da · report
d8f1a24b68aa0b29 · report
1ac664c178170ffe · report
8be19ea313e7777e · report
ed15506c976a883e · report
ccdc152785a294d2 · report
6014219e7ea97f79 · report
248f0c82db73b84d · report
ba426aae4d6a9c16 · report
a0131fb70c267a9e · report
46467acb70052484 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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