Papers › MobileNetV4 -- Universal Models for the Mobile Ecosystem

MobileNetV4 -- Universal Models for the Mobile Ecosystem

16 Apr 2024arXiv:2404.10518archive 2025-07-28

Danfeng Qin, Chas Leichner, Manolis Delakis, Marco Fornoni, Shixin Luo, Fan Yang, Weijun Wang, Colby Banbury, Chengxi Ye, Berkin Akin, Vaibhav Aggarwal, Tenghui Zhu, Daniele Moro, Andrew Howard

We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the Universal Inverted Bottleneck (UIB) search block, a unified and flexible structure that merges Inverted Bottleneck (IB), ConvNext, Feed Forward Network (FFN), and a novel Extra Depthwise (ExtraDW) variant. Alongside UIB, we present Mobile MQA, an attention block tailored for mobile accelerators, delivering a significant 39% speedup. An optimized neural architecture search (NAS) recipe is also introduced which improves MNv4 search effectiveness. The integration of UIB, Mobile MQA and the refined NAS recipe results in a new suite of MNv4 models that are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU - a characteristic not found in any other models tested. Finally, to further boost accuracy, we introduce a novel distillation technique. Enhanced by this technique, our MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms.

PaperPDFCodeCode Syntology ran

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="2404.10518")

Code

Syntology Ran 6 of 13 code samples harvested from 4 repositories linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · honoured contract; 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 13 samples from 4 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

huggingface/pytorch-image-models mentioned on GitHubpytorchApache-2.0 report
jaiwei98/MobileNetV4-pytorch mentioned on GitHubpytorch report
jiaowoguanren0615/MobileNetV4 mentioned on GitHubpytorchMIT report
junaidaliop/MobileNetV4 mentioned on GitHubpytorch report
wh1090220084/mobilenetv4_pytorch mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

13 samples harvested; 6 ran; 3 honoured the contract we drafted; 7 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.

3ran · honoured contract
2ran · our draft was wrong
1ran
7unverified

Licence: 1 of the 13 samples is 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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.

accuracy_np jiaowoguanren0615/MobileNetV4/onnx_validate.py community (archive-listed) ran MIT (permissive) · ce856d9e51a3df05 · report
block_spec_values_to_list junaidaliop/MobileNetV4/MobileNetV4.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0e20d40db79fb5c0 · report
conv_2d jaiwei98/MobileNetV4-pytorch/mobilenet/mobilenetv4.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 067715c0c5734d87 · report
make_divisible jaiwei98/MobileNetV4-pytorch/mobilenet/mobilenetv4.py community (archive-listed) ran · honoured contract MIT (permissive) · 6b65b07f03530a4d · report
make_divisible wh1090220084/mobilenetv4_pytorch/mobilenetv4.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 231ab9d94ccd8ac2 · report
make_divisible jiaowoguanren0615/MobileNetV4/models/blocks.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 24400bc088ed228d · report
build_blocks jaiwei98/MobileNetV4-pytorch/mobilenet/mobilenetv4.py community (archive-listed) unverified MIT (permissive) · a7ca97f43224d68c · report
max_voting jiaowoguanren0615/MobileNetV4/optim_AUC.py community (archive-listed) unverified MIT (permissive) · 968810e99c2743be · report
num_groups jiaowoguanren0615/MobileNetV4/models/blocks.py community (archive-listed) unverified MIT (permissive) · 3858599774ed62d7 · report
onnx_forward jiaowoguanren0615/MobileNetV4/onnx_export.py community (archive-listed) unverified MIT (permissive) · 657331b58c43b3fc · report
reparameterize_model jiaowoguanren0615/MobileNetV4/onnx_export.py community (archive-listed) unverified MIT (permissive) · 57c0e0444e26c7e2 · report
resolve_act_layer jiaowoguanren0615/MobileNetV4/models/model_utils.py community (archive-listed) unverified MIT (permissive) · 65913dcf1b9ca4d1 · report
resolve_bn_args jiaowoguanren0615/MobileNetV4/models/model_utils.py community (archive-listed) unverified MIT (permissive) · ad5c779c4dbc8362 · report

Tasks

Image ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MNv4-Hybrid-L Top 1 Accuracy 83.4% #426 of 1060 Archive leaderboard report
Image Classification ImageNet MNv4-Conv-L Top 1 Accuracy 82.9% #485 of 1060 Archive leaderboard report
Image Classification ImageNet MNv4-Hybrid-M Top 1 Accuracy 80.7% #684 of 1060 Archive leaderboard report
Image Classification ImageNet MNv4-Conv-M Top 1 Accuracy 79.9% #729 of 1060 Archive leaderboard report
Image Classification ImageNet MNv4-Conv-S Top 1 Accuracy 73.8% #984 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: MobileNet-V4

MobileNet-V4

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