2016 SqueezeNetAlexNetLevelAccuracyw

• (Iandola et al., 2016) ⇒ Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. (2016). “SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and $\lt$0.5MB Model Size.”. arXiv e-prints: 1602.07360.

Subject Headings: Squeezenet; Deep Learning Neural Network; Deep Convolutional Neural Network; Convolutional Neural Network

Cited By

• http://scholar.google.com/scholar?q=%222016%22+SqueezeNet%3A+AlexNet-level+Accuracy+with+50x+Fewer+Parameters+and+%24%5Clt%240.5MB+Model+Size
• ICLR 2017 conference submission: https://openreview.net/forum?id=S1xh5sYgx&noteId=S1xh5sYgx
• Lecture Notes, Columbia University E6894, Spring 2017: http://llcao.net/cu-deeplearning17/pp/class10_SqueezeNet.pdf

Quotes

Author Keywords

• Computer Science; Computer Vision; Pattern Recognition; Artificial Intelligence

Abstract

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 SqueezeNetAlexNetLevelAccuracyw	Forrest N. Iandola Song Han Matthew W. Moskewicz Khalid Ashraf William J. Dally Kurt Keutzer			SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and $\lt$0.5MB Model Size