# Fighting Quantization Bias With Bias

arXiv: https://arxiv.org/abs/1906.03193 · HTML: https://mlsanity.com/paper/1906.03193/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

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

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [Generative Zero-shot Network Quantization](https://mlsanity.com/paper/2101.08430/) (2021)
- [Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks](https://mlsanity.com/paper/2308.10438/) (2023)
- [HPTQ: Hardware-Friendly Post Training Quantization](https://mlsanity.com/paper/2109.09113/) (2021)
- [EQ-Net: Elastic Quantization Neural Networks](https://mlsanity.com/paper/2308.07650/) (2023)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [GenQ: Quantization in Low Data Regimes with Generative Synthetic Data](https://mlsanity.com/paper/2312.05272/) (2023)
- [Quantized Prompt for Efficient Generalization of Vision-Language Models](https://mlsanity.com/paper/2407.10704/) (2024)
- [Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart](https://mlsanity.com/paper/2412.15846/) (2024)
- [Task Vector Quantization for Memory-Efficient Model Merging](https://mlsanity.com/paper/2503.06921/) (2025)
- [To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding](https://mlsanity.com/paper/2203.14646/) (2022)
- [Vertical Layering of Quantized Neural Networks for Heterogeneous Inference](https://mlsanity.com/paper/2212.05326/) (2022)
- [Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs](https://mlsanity.com/paper/2311.12359/) (2023)
- [Symmetry Regularization and Saturating Nonlinearity for Robust Quantization](https://mlsanity.com/paper/2208.00338/) (2022)
- [Efficient Adaptive Activation Rounding for Post-Training Quantization](https://mlsanity.com/paper/2208.11945/) (2022)
- [QFT: Post-training quantization via fast joint finetuning of all degrees of freedom](https://mlsanity.com/paper/2212.02634/) (2022)
- [ACQ: Improving Generative Data-free Quantization Via Attention Correction](https://mlsanity.com/paper/2301.07266/) (2023)
- [ResQ: Residual Quantization for Video Perception](https://mlsanity.com/paper/2308.09511/) (2023)
- [Differentiable Search for Finding Optimal Quantization Strategy](https://mlsanity.com/paper/2404.08010/) (2024)
- [The Cambrian Explosion of Mixed-Precision Matrix Multiplication for Quantized Deep Learning Inference](https://mlsanity.com/paper/2506.11728/) (2025)
- [Rescaling-Aware Training for Efficient Deployment of Deep Learning Models on Full-Integer Hardware](https://mlsanity.com/paper/2510.11484/) (2025)
- [SigmaQuant: Hardware-Aware Heterogeneous Quantization Method for Edge DNN Inference](https://mlsanity.com/paper/2602.22136/) (2026)
- [Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization](https://mlsanity.com/paper/2105.01868/) (2021)
- [Post-training Model Quantization Using GANs for Synthetic Data Generation](https://mlsanity.com/paper/2305.06052/) (2023)
- [MRQ:Support Multiple Quantization Schemes through Model Re-Quantization](https://mlsanity.com/paper/2308.01867/) (2023)
- [Q&C: When Quantization Meets Cache in Efficient Image Generation](https://mlsanity.com/paper/2503.02508/) (2025)
- [Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?](https://mlsanity.com/paper/2508.07142/) (2025)
- [BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?](https://mlsanity.com/paper/2511.17633/) (2025)

## Abstract (arXiv)

Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network to low precision degrades its performance. Crucially, networks that are designed for embedded applications usually suffer from increased degradation since they have less redundancy. This is most evident for the ubiquitous MobileNet architecture which requires a costly quantization-aware training cycle to achieve acceptable performance when quantized to 8-bits. In this paper, we trace the source of the degradation in MobileNets to a shift in the mean activation value. This shift is caused by an inherent bias in the quantization process which builds up across layers, shifting all network statistics away from the learned distribution. We show that this phenomenon happens in other architectures as well. We propose a simple remedy - compensating for the quantization induced shift by adding a constant to the additive bias term of each channel. We develop two simple methods for estimating the correction constants - one using iterative evaluation of the quantized network and one where the constants are set using a short training phase. Both methods are fast and require only a small amount of unlabeled data, making them appealing for rapid deployment of neural networks. Using the above methods we are able to match the performance of training-based quantization of MobileNets at a fraction of the cost.