arXiv (Cornell University)· 2017· Preprint
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- 9,901citations
- 2017year
Short summary
MobileNets are a new class of efficient neural networks using depth-wise separable convolutions, enabling a trade-off between latency and accuracy via simple hyper-parameters for mobile vision tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces MobileNets, a class of efficient neural networks for mobile vision.
- Utilizes depth-wise separable convolutions for lightweight deep network construction.
- Features two global hyper-parameters to efficiently trade off latency and accuracy.
- Demonstrates strong performance on ImageNet and effectiveness in diverse applications.
AI-generated from the title and abstract; the full text is not read.
Abstract
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
The authors' abstract, as published at the source. arXiv (Cornell University), 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science