# SqueezeNext: Hardware-Aware Neural Network Design

Source: [SqueezeNext: Hardware-Aware Neural Network Design](<https://www.sota2.com/research/paper/68fa69cf1e209131cea244c8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:09:38.543Z

Authors: Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter Jin, Sicheng Zhao, Kurt Keutzer

Published: 2018-03-23T16:40:30.000Z

## Abstract

One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks. In this work, we introduce SqueezeNext, a new family of neural network architectures whose design was guided by considering previous architectures such as SqueezeNet, as well as by simulation results on a neural network accelerator. This new network is able to match AlexNet's accuracy on the ImageNet benchmark with $112\\times$ fewer parameters, and one of its deeper variants is able to achieve VGG-19 accuracy with only 4.4 Million parameters, ($31\\times$ smaller than VGG-19). SqueezeNext also achieves better top-5 classification accuracy with $1.3\\times$ fewer parameters as compared to MobileNet, but avoids using depthwise-separable convolutions that are inefficient on some mobile processor platforms. This wide range of accuracy gives the user the ability to make speed-accuracy tradeoffs, depending on the available resources on the target hardware. Using hardware simulation results for power and inference speed on an embedded system has guided us to design variations of the baseline model that are $2.59\\times$/$8.26\\times$ faster and $2.25\\times$/$7.5\\times$ more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet (val) (Top-1 and Top-5 Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-top-1-and-top-5-accuracy.md>): Image Classification; ImageNet (val); Top-1 Accuracy: 67.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1803.10615>)

[PDF](<https://arxiv.org/pdf/1803.10615.pdf>)
