# SqueezeNext: Hardware-Aware Neural Network Design

arXiv: https://arxiv.org/abs/1803.10615 · HTML: https://mlsanity.com/paper/1803.10615/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2018.

## Built on by (most cited first, 30 of 61)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [I-BERT: Integer-only BERT Quantization](https://mlsanity.com/paper/2101.01321/) (2021)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation](https://mlsanity.com/paper/2202.07471/) (2022)
- [DarkIR: Robust Low-Light Image Restoration](https://mlsanity.com/paper/2412.13443/) (2024)
- [Hessian-Aware Pruning and Optimal Neural Implant](https://mlsanity.com/paper/2101.08940/) (2021)
- [DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos](https://mlsanity.com/paper/2304.06544/) (2023)
- [FEAR: Fast, Efficient, Accurate and Robust Visual Tracker](https://mlsanity.com/paper/2112.07957/) (2021)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [Applications and Techniques for Fast Machine Learning in Science](https://mlsanity.com/paper/2110.13041/) (2021)
- [Sequencer: Deep LSTM for Image Classification](https://mlsanity.com/paper/2205.01972/) (2022)
- [Searching for Fast Model Families on Datacenter Accelerators](https://mlsanity.com/paper/2102.05610/) (2021)
- [It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher](https://mlsanity.com/paper/2203.17008/) (2022)
- [TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge](https://mlsanity.com/paper/2307.09988/) (2023)
- [GhostNets on Heterogeneous Devices via Cheap Operations](https://mlsanity.com/paper/2201.03297/) (2022)
- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data](https://mlsanity.com/paper/2104.11629/) (2021)
- [Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics](https://mlsanity.com/paper/2104.11849/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization](https://mlsanity.com/paper/2109.00212/) (2021)
- [MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis](https://mlsanity.com/paper/2104.04767/) (2021)
- [Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution](https://mlsanity.com/paper/2201.01458/) (2022)
- [Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques](https://mlsanity.com/paper/2112.15131/) (2021)
- [GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting](https://mlsanity.com/paper/2503.04333/) (2025)
- [Mixed-Precision Neural Networks: A Survey](https://mlsanity.com/paper/2208.06064/) (2022)
- [Building Variable-sized Models via Learngene Pool](https://mlsanity.com/paper/2312.05743/) (2023)
- [Frequency learning for structured CNN filters with Gaussian fractional derivatives](https://mlsanity.com/paper/2111.06660/) (2021)
- [A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics](https://mlsanity.com/paper/2112.02834/) (2021)
- [EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization](https://mlsanity.com/paper/2309.11531/) (2023)
- [YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers](https://mlsanity.com/paper/2203.03794/) (2022)

## Abstract (arXiv)

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× fewer parameters, and one of its deeper variants is able to achieve VGG-19 accuracy with only 4.4 Million parameters, (31× smaller than VGG-19). SqueezeNext also achieves better top-5 classification accuracy with 1.3× 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×/8.26× faster and 2.25×/7.5× more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation.