Wikipedia

MobileNet

MobileNet is a family of convolutional neural network (CNN) architectures designed for image classification, object detection, and other computer vision tasks. They are designed for small size, low latency, and low power consumption, making them suitable for on-device inference and edge computing on resource-constrained devices like mobile phones and embedded systems. They were originally designed to be run efficiently on mobile devices with TensorFlow Lite.

MobileNet
Developer(s)Google
Initial releaseApril 2017
Stable release
v4 / September 2024
Repositorygithub.com/tensorflow/models/tree/master/research/slim/nets/mobilenet
Written inPython
LicenseApache License 2.0

The need for efficient deep learning models on mobile devices led researchers at Google to develop MobileNet. As of October 2024, the family has four versions, each improving upon the previous one in terms of performance and efficiency.

Features

edit

V1

edit

MobileNetV1 was published in April 2017.[1][2] Its main architectural innovation was incorporation of depthwise separable convolutions. It was first developed by Laurent Sifre during an internship at Google Brain in 2013 as an architectural variation on AlexNet to improve convergence speed and model size.[3]

The depthwise separable convolution decomposes a single standard convolution into two convolutions: a depthwise convolution that filters each input channel independently and a pointwise convolution (  convolution) that combines the outputs of the depthwise convolution. This factorization significantly reduces computational cost.

The MobileNetV1 has two hyperparameters: a width multiplier   that controls the number of channels in each layer. Smaller values of   lead to smaller and faster models, but at the cost of reduced accuracy, and a resolution multiplier  , which controls the input resolution of the images. Lower resolutions result in faster processing but potentially lower accuracy.

V2

edit

MobileNetV2 was published in March 2019.[4][5] It uses inverted residual layers and linear bottlenecks.

Inverted residuals modify the traditional residual block structure. Instead of compressing the input channels before the depthwise convolution, they expand them. This expansion is followed by a   depthwise convolution and then a   projection layer that reduces the number of channels back down. This inverted structure helps to maintain representational capacity by allowing the depthwise convolution to operate on a higher-dimensional feature space, thus preserving more information flow during the convolutional process.

Linear bottlenecks removes the typical ReLU activation function in the projection layers. This was rationalized by arguing that that nonlinear activation loses information in lower-dimensional spaces, which is problematic when the number of channels is already small.

V3

edit

MobileNetV3 was published in 2019.[6][7] The publication included MobileNetV3-Small, MobileNetV3-Large, and MobileNetEdgeTPU (optimized for Pixel 4). They were found by a form of neural architecture search (NAS) that takes mobile latency into account, to achieve good trade-off between accuracy and latency.[8][9] It used piecewise-linear approximations of swish and sigmoid activation functions (which they called "h-swish" and "h-sigmoid"), squeeze-and-excitation modules,[10] and the inverted bottlenecks of MobileNetV2.

V4

edit

MobileNetV4 was published in September 2024.[11][12] The publication included a large number of architectures found by NAS. Compared to the architectural modules used in V3, the V4 series included the "universal inverted bottleneck", which includes both inverted residual and inverted bottleneck as special cases, and attention modules with multi-query attention.[13]

See also

edit
edit
  • "models/research/slim/nets/mobilenet at master · tensorflow/models". GitHub. Retrieved 2024-10-18.
  • "Keras documentation: MobileNet, MobileNetV2, and MobileNetV3". Keras. Retrieved October 18, 2024.

References

edit
  1. ^ Howard, Andrew G.; Zhu, Menglong; Chen, Bo; Kalenichenko, Dmitry; Wang, Weijun; Weyand, Tobias; Andreetto, Marco; Adam, Hartwig (2017-04-16), MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, arXiv:1704.04861
  2. ^ "MobileNets: Open-Source Models for Efficient On-Device Vision". research.google. June 14, 2017. Retrieved 2024-10-18.
  3. ^ Chollet, François (2017). "Xception: Deep Learning with Depthwise Separable Convolutions". 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1800–1807. arXiv:1610.02357. doi:10.1109/CVPR.2017.195. ISBN 978-1-5386-0457-1.
  4. ^ Sandler, Mark; Howard, Andrew; Zhu, Menglong; Zhmoginov, Andrey; Chen, Liang-Chieh (2019-03-21), MobileNetV2: Inverted Residuals and Linear Bottlenecks, arXiv:1801.04381
  5. ^ "MobileNetV2: The Next Generation of On-Device Computer Vision Networks". research.google. April 3, 2018. Retrieved 2024-10-18.
  6. ^ "Introducing the Next Generation of On-Device Vision Models: MobileNetV3 and Mobi". research.google. November 13, 2019. Retrieved 2024-10-18.
  7. ^ Howard, Andrew; Sandler, Mark; Chu, Grace; Chen, Liang-Chieh; Chen, Bo; Tan, Mingxing; Wang, Weijun; Zhu, Yukun; Pang, Ruoming; Vasudevan, Vijay; Le, Quoc V.; Adam, Hartwig (2019). "Searching for MobileNetV3": 1314–1324. arXiv:1905.02244. {{cite journal}}: Cite journal requires |journal= (help)
  8. ^ Tan, Mingxing; Chen, Bo; Pang, Ruoming; Vasudevan, Vijay; Sandler, Mark; Howard, Andrew; Le, Quoc V. (June 2019). "MnasNet: Platform-Aware Neural Architecture Search for Mobile". 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. pp. 2815–2823. arXiv:1807.11626. doi:10.1109/CVPR.2019.00293. ISBN 978-1-7281-3293-8.
  9. ^ Yang, Tien-Ju; Howard, Andrew; Chen, Bo; Zhang, Xiao; Go, Alec; Sandler, Mark; Sze, Vivienne; Adam, Hartwig (2018). "NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications": 285–300. arXiv:1804.03230. {{cite journal}}: Cite journal requires |journal= (help)
  10. ^ Hu, Jie; Shen, Li; Sun, Gang (2018). "Squeeze-and-Excitation Networks": 7132–7141. {{cite journal}}: Cite journal requires |journal= (help)
  11. ^ Qin, Danfeng; Leichner, Chas; Delakis, Manolis; Fornoni, Marco; Luo, Shixin; Yang, Fan; Wang, Weijun; Banbury, Colby; Ye, Chengxi (2024-09-29), MobileNetV4 -- Universal Models for the Mobile Ecosystem, arXiv:2404.10518
  12. ^ Wightman, Ross. "MobileNet-V4 (now in timm)". huggingface.co. Retrieved 2024-10-18.
  13. ^ Shazeer, Noam (2019-11-05), Fast Transformer Decoding: One Write-Head is All You Need, arXiv:1911.02150, retrieved 2024-10-19
Retrieved from "https://en.wikipedia.org/w/index.php?title=MobileNet&oldid=1251964038"