MobileOne: An Improved One millisecond Mobile Backbone

TL;DR

MobileOne introduces a new neural network backbone optimized for mobile devices, achieving under 1 ms inference time on an iPhone12 with high accuracy, outperforming existing efficient models in speed and performance across multiple tasks.

Contribution

The paper presents MobileOne, a novel efficient backbone architecture designed specifically for mobile deployment, with extensive analysis and optimization to reduce latency and improve accuracy.

Findings

MobileOne achieves under 1 ms inference on iPhone12.

MobileOne outperforms EfficientNet in accuracy at similar latency.

MobileOne generalizes well across classification, detection, and segmentation tasks.

Abstract

Efficient neural network backbones for mobile devices are often optimized for metrics such as FLOPs or parameter count. However, these metrics may not correlate well with latency of the network when deployed on a mobile device. Therefore, we perform extensive analysis of different metrics by deploying several mobile-friendly networks on a mobile device. We identify and analyze architectural and optimization bottlenecks in recent efficient neural networks and provide ways to mitigate these bottlenecks. To this end, we design an efficient backbone MobileOne, with variants achieving an inference time under 1 ms on an iPhone12 with 75.9% top-1 accuracy on ImageNet. We show that MobileOne achieves state-of-the-art performance within the efficient architectures while being many times faster on mobile. Our best model obtains similar performance on ImageNet as MobileFormer while being 38x faster. Our model obtains 2.3% better top-1 accuracy on ImageNet than EfficientNet at similar latency. Furthermore, we show that our model generalizes to multiple tasks - image classification, object detection, and semantic segmentation with significant improvements in latency and accuracy as compared to existing efficient architectures when deployed on a mobile device. Code and models are available at https://github.com/apple/ml-mobileone