mlsanityData to 14 Oct 2026

SqueezeNext: Hardware-Aware Neural Network Design

arXiv 1803.10615 ↗First posted 23 Mar 2018cs.NEcited by 61

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 16; 2023: 9; 2024: 7; 2025: 5; 2026: 6.

61 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  2. 2021I-BERT: Integer-only BERT Quantizationcited by 255
  3. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  4. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 55
  5. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  6. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 45
  7. 2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
  8. 2021FEAR: Fast, Efficient, Accurate and Robust Visual Trackercited by 38
  9. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  10. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  11. 2022Sequencer: Deep LSTM for Image Classificationcited by 23
  12. 2021Searching for Fast Model Families on Datacenter Acceleratorscited by 22
38 more
  1. 2022It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teachercited by 20
  2. 2023TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edgecited by 18
  3. 2022GhostNets on Heterogeneous Devices via Cheap Operationscited by 15
  4. 2021Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-designcited by 13
  5. 2021DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Datacited by 12
  6. 2021Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamicscited by 12
  7. 2022Neural Architecture Search for Dense Prediction Tasks in Computer Visioncited by 12
  8. 2021Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantizationcited by 11
  9. 2021MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesiscited by 10
  10. 2022Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolutioncited by 10
  11. 2021Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniquescited by 9
  12. 2025GaussianVideo: Efficient Video Representation and Compression by Gaussian Splattingcited by 8
  13. 2022Mixed-Precision Neural Networks: A Surveycited by 7
  14. 2023Building Variable-sized Models via Learngene Poolcited by 7
  15. 2021Frequency learning for structured CNN filters with Gaussian fractional derivativescited by 6
  16. 2021A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statisticscited by 6
  17. 2023EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimizationcited by 6
  18. 2022YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollerscited by 4
  19. 2022Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networkscited by 4
  20. 2022Lightweight and Progressively-Scalable Networks for Semantic Segmentationcited by 4
  21. 2024TeLU Activation Function for Fast and Stable Deep Learningcited by 4
  22. 2022A memory-efficient neural ODE framework based on high-level adjoint differentiationcited by 3
  23. 2025Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effectscited by 3
  24. 2021FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrayscited by 2
  25. 2022EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting Systemcited by 2
  26. 2022Efficient ML Models for Practical Secure Inferencecited by 2
  27. 2023Gated Compression Layers for Efficient Always-On Modelscited by 2
  28. 2025Green Federated Learning via Carbon-Aware Client and Time Slot Schedulingcited by 2
  29. 2021AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applicationscited by 1
  30. 2021Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edgecited by 1
  31. 2022Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Surveycited by 1
  32. 2023Tensor-Aware Energy Accountingcited by 1
  33. 2023Cooperative Learning for Cost-Adaptive Inferencecited by 1
  34. 2024NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigationcited by 1
  35. 2024AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devicescited by 1
  36. 2026Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systemscited by 1
  37. 2022Standard Deviation-Based Quantization for Deep Neural Networkscited by 0
  38. 2022PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detectioncited by 0

50 most cited of 61 All 61 (JSON)