MobileOne: An Improved One millisecond Mobile Backbone

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

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification ImageNet MobileOne-S4 (distill) Top 1 Accuracy 81.4% # 581
Number of params 14.8M # 509
GFLOPs 2.9 # 171
Image Classification ImageNet MobileOne-S3 (distill) Top 1 Accuracy 80.0% # 659
Number of params 10.1M # 471
GFLOPs 1.8 # 138
Image Classification ImageNet MobileOne-S2 (distill) Top 1 Accuracy 79.1% # 709
Number of params 7.8M # 454
GFLOPs 1.3 # 118
Image Classification ImageNet MobileOne-S1 (distill) Top 1 Accuracy 77.4% # 804
Number of params 4.8M # 389
GFLOPs 0.825 # 96
Image Classification ImageNet MobileOne-S0 (distill) Top 1 Accuracy 72.5% # 918
Number of params 2.1M # 351
GFLOPs 0.275 # 22
Image Classification ImageNet MobileOne-S0 Top 1 Accuracy 71.4% # 932
Number of params 2.1M # 351
GFLOPs 0.275 # 22
Image Classification ImageNet MobileOne-S1 Top 1 Accuracy 75.9 # 852
Number of params 4.8M # 389
GFLOPs 0.825 # 96
Image Classification ImageNet MobileOne-S2 Top 1 Accuracy 77.4% # 804
Number of params 7.8 # 1
GFLOPs 1.3 # 118
Image Classification ImageNet MobileOne-S3 Top 1 Accuracy 78.1% # 780
Number of params 10.1M # 471
GFLOPs 1.8 # 138
Image Classification ImageNet MobileOne-S4 Top 1 Accuracy 79.4% # 690
Number of params 14.8M # 509
GFLOPs 2.9 # 171

Methods