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

ICLR 2022  ·  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:

PDF Abstract ICLR 2022 PDF ICLR 2022 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Image Classification ImageNet MobileViT-S Top 1 Accuracy 78.4% # 601
Top 5 Accuracy 94.1% # 175
Number of params 5.6M # 326
Image Classification ImageNet MobileViT-XS Top 1 Accuracy 74.8% # 713
Top 5 Accuracy 92.3% # 228
Number of params 2.3 M # 3
GFLOPs 0.7 # 77