</> Code with Papers by Syntology

Papers › MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of...

MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features

30 Sep 2022arXiv:2209.15159archive 2025-07-28

Shakti N. Wadekar, Abhishek Chaurasia

MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art results, the fusion block inside MobileViTv1-block, creates scaling challenges and has a complex learning task. We propose changes to the fusion block that are simple and effective to create MobileViTv3-block, which addresses the scaling and simplifies the learning task. Our proposed MobileViTv3-block used to create MobileViTv3-XXS, XS and S models outperform MobileViTv1 on ImageNet-1k, ADE20K, COCO and PascalVOC2012 datasets. On ImageNet-1K, MobileViTv3-XXS and MobileViTv3-XS surpasses MobileViTv1-XXS and MobileViTv1-XS by 2% and 1.9% respectively. Recently published MobileViTv2 architecture removes fusion block and uses linear complexity transformers to perform better than MobileViTv1. We add our proposed fusion block to MobileViTv2 to create MobileViTv3-0.5, 0.75 and 1.0 models. These new models give better accuracy numbers on ImageNet-1k, ADE20K, COCO and PascalVOC2012 datasets as compared to MobileViTv2. MobileViTv3-0.5 and MobileViTv3-0.75 outperforms MobileViTv2-0.5 and MobileViTv2-0.75 by 2.1% and 1.0% respectively on ImageNet-1K dataset. For segmentation task, MobileViTv3-1.0 achieves 2.07% and 1.1% better mIOU compared to MobileViTv2-1.0 on ADE20K dataset and PascalVOC2012 dataset respectively. Our code and the trained models are available at: https://github.com/micronDLA/MobileViTv3

PaperPDFCode

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

Code

microndla/mobilevitv3 officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
jaiwei98/mobile-vit-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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationObject DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MobileViTv3-S GFLOPs 1.841 #765 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-S Number of params 5.8M #765 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-S Top 1 Accuracy 79.3% #765 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-1.0 GFLOPs 1.876 #815 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-1.0 Top 1 Accuracy 78.64% #815 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XS GFLOPs 0.927 #902 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XS Number of params 2.5M #902 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XS Top 1 Accuracy 76.7% #902 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.75 GFLOPs 1.064 #911 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.75 Number of params 3M #911 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.75 Top 1 Accuracy 76.55% #911 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.5 GFLOPs 0.481 #998 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.5 Number of params 1.4M #998 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-0.5 Top 1 Accuracy 72.33% #998 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XXS GFLOPs 0.289 #1015 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XXS Number of params 1.2M #1015 of 1060 Archive leaderboard report
Image Classification ImageNet MobileViTv3-XXS Top 1 Accuracy 70.98% #1015 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: MobileViTv3

1x1 ConvolutionAttentionBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutLayer NormalizationLinear LayerMobileViTv2MobileViTv3Multi-Head AttentionPointwise ConvolutionResidual ConnectionSoftmaxVision 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