arXiv (Cornell University)· 2016· Preprint
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- 5,926citations
- 2016year
Short summary
SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and a model size under 0.5MB.
AI-generated from the title and abstract; the full text is not read.
Key points
- SqueezeNet achieves AlexNet-level accuracy on the ImageNet dataset.
- The SqueezeNet architecture has 50x fewer parameters than AlexNet.
- SqueezeNet can be compressed to a model size of less than 0.5MB.
- Smaller model size offers advantages in distributed training, model export, and hardware deployment.
AI-generated from the title and abstract; the full text is not read.
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
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · 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