# 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

arXiv: https://arxiv.org/abs/2104.11849 · HTML: https://mlsanity.com/paper/2104.11849/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 24 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Convolutional Neural Networks using Logarithmic Data Representation](https://mlsanity.com/paper/1603.01025/) (2016)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [Robust Quantization: One Model to Rule Them All](https://mlsanity.com/paper/2002.07686/) (2020)
- [SqueezeNext: Hardware-Aware Neural Network Design](https://mlsanity.com/paper/1803.10615/) (2018)
- [DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures](https://mlsanity.com/paper/1908.09979/) (2019)
- [Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization](https://mlsanity.com/paper/1902.01917/) (2019)
- [A Quantization-Friendly Separable Convolution for MobileNets](https://mlsanity.com/paper/1803.08607/) (2018)
- [Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks](https://mlsanity.com/paper/2011.14578/) (2020)
- [FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints](https://mlsanity.com/paper/2011.14586/) (2020)

## Built on by (most cited first, 12 of 12)

- [Make RepVGG Greater Again: A Quantization-aware Approach](https://mlsanity.com/paper/2212.01593/) (2022)
- [Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective](https://mlsanity.com/paper/2303.11906/) (2023)
- [Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2312.09028/) (2023)
- [Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime](https://mlsanity.com/paper/2207.08820/) (2022)
- [Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors](https://mlsanity.com/paper/2201.11651/) (2022)
- [An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks](https://mlsanity.com/paper/2111.08163/) (2021)
- [GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks](https://mlsanity.com/paper/2208.12489/) (2022)
- [On Calibration of Modern Quantized Efficient Neural Networks](https://mlsanity.com/paper/2309.13866/) (2023)
- [LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices](https://mlsanity.com/paper/2503.15889/) (2025)
- [Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization](https://mlsanity.com/paper/2506.10463/) (2025)
- [Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective](https://mlsanity.com/paper/2606.15161/) (2026)
- [GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks](https://mlsanity.com/paper/2309.13773/) (2023)

## Abstract (arXiv)

As the "Mobile AI" revolution continues to grow, so does the need to understand the behaviour of edge-deployed deep neural networks. In particular, MobileNets are the go-to family of deep convolutional neural networks (CNN) for mobile. However, they often have significant accuracy degradation under post-training quantization. While studies have introduced quantization-aware training and other methods to tackle this challenge, there is limited understanding into why MobileNets (and potentially depthwise-separable CNNs (DWSCNN) in general) quantize so poorly compared to other CNN architectures. Motivated to gain deeper insights into this phenomenon, we take a different strategy and study the multi-scale distributional dynamics of MobileNet-V1, a set of smaller DWSCNNs, and regular CNNs. Specifically, we investigate the impact of quantization on the weight and activation distributional dynamics as information propagates from layer to layer, as well as overall changes in distributional dynamics at the network level. This fine-grained analysis revealed significant dynamic range fluctuations and a "distributional mismatch" between channelwise and layerwise distributions in DWSCNNs that lead to increasing quantized degradation and distributional shift during information propagation. Furthermore, analysis of the activation quantization errors show that there is greater quantization error accumulation in DWSCNN compared to regular CNNs. The hope is that such insights can lead to innovative strategies for reducing such distributional dynamics changes and improve post-training quantization for mobile.