MobileOne: An Improved One millisecond Mobile Backbone
By Pavan Kumar Anasosalu Vasu, J. Gabriel, Jeff J. Zhu, Oncel Tuzel, Anurag Ranjan. Computer Vision and Pattern Recognition, 2022
336 citations recorded by the source corpus.
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 38×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
Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/d83105503f3b7c6403e812cc1d354b270ab4c048
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (2023, neutral): “Prior work on efficient models considers light-weight architectures [41, 56, 101, 155, 165, 195], efficient input processing [43, 44, 73, 102, 156], or inference optimizations [39, 58, 121, 174, 206].”
- MobileNetV4 - Universal Models for the Mobile Ecosystem (2024, positive): “We benchmark our models against the leading efficient models, including hybrid (MiT-EfficientViT [14], FastViT [45], NextViT [28]) and convolutional models (MobileOne [46], ConvNext [34], and previous MobileNets [21] [38] [20]) based on their reported Top-1 Accuracies and our latency evaluations.”
- Rep ViT: Revisiting Mobile CNN From ViT Perspective (2023, methodology): “These studies demonstrate that lightweight ViTs [34, 45, 47] can achieve lower latency on mobile devices while outperforming lightweight CNNs [25, 51, 58], as shown in Figure 1.”
- Rewrite the Stars (2024, positive): “These include depth-wise convolution [28, 46], feature re-use [6, 19], and re-parameterization [55], among others.”