SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

TL;DR

SqueezeNet is a compact deep neural network architecture that achieves AlexNet-level accuracy on ImageNet with 50 times fewer parameters and can be compressed to under 0.5MB, enabling efficient deployment and communication.

Contribution

The paper introduces SqueezeNet, a novel small DNN architecture that maintains high accuracy while significantly reducing model size and parameters.

Findings

Achieves AlexNet-level accuracy with 50x fewer parameters

Compresses to less than 0.5MB, 510x smaller than AlexNet

Facilitates deployment on hardware with limited memory

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