# MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization

arXiv: https://arxiv.org/abs/2305.08117 · HTML: https://mlsanity.com/paper/2305.08117/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 14 May 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Deep Information Propagation](https://mlsanity.com/paper/1611.01232/) (2016)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [Adaptive Quantization for Deep Neural Network](https://mlsanity.com/paper/1712.01048/) (2017)
- [AdaBits: Neural Network Quantization with Adaptive Bit-Widths](https://mlsanity.com/paper/1912.09666/) (2019)
- [Robust Quantization: One Model to Rule Them All](https://mlsanity.com/paper/2002.07686/) (2020)
- [FracBits: Mixed Precision Quantization via Fractional Bit-Widths](https://mlsanity.com/paper/2007.02017/) (2020)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Any-Precision Deep Neural Networks](https://mlsanity.com/paper/1911.07346/) (2019)
- [Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples](https://mlsanity.com/paper/2111.02625/) (2021)
- [Bit-Mixer: Mixed-precision networks with runtime bit-width selection](https://mlsanity.com/paper/2103.17267/) (2021)
- [Distance-aware Quantization](https://mlsanity.com/paper/2108.06983/) (2021)
- [Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss](https://mlsanity.com/paper/2109.02100/) (2021)
- [Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach](https://mlsanity.com/paper/2204.09992/) (2022)
- [Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths](https://mlsanity.com/paper/2103.01435/) (2021)
- [PalQuant: Accelerating High-precision Networks on Low-precision Accelerators](https://mlsanity.com/paper/2208.01944/) (2022)
- [ACQ: Improving Generative Data-free Quantization Via Attention Correction](https://mlsanity.com/paper/2301.07266/) (2023)
- [Learning Accurate Performance Predictors for Ultrafast Automated Model Compression](https://mlsanity.com/paper/2304.06393/) (2023)

## Built on by (most cited first, 6 of 6)

- [I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization](https://mlsanity.com/paper/2311.10126/) (2023)
- [DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers](https://mlsanity.com/paper/2408.03291/) (2024)
- [TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision](https://mlsanity.com/paper/2506.11431/) (2025)
- [Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling](https://mlsanity.com/paper/2510.20673/) (2025)
- [CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration](https://mlsanity.com/paper/2510.03038/) (2025)
- [Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning](https://mlsanity.com/paper/2603.12832/) (2026)

## Abstract (arXiv)

Arbitrary bit-width network quantization has received significant attention due to its high adaptability to various bit-width requirements during runtime. However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by switching weight and activations bit-widths, leading to limited performance. To address this issue, we propose MBQuant, a novel method that utilizes a multi-branch topology for arbitrary bit-width quantization. MBQuant duplicates the network body into multiple independent branches, where the weights of each branch are quantized to a fixed 2-bit and the activations remain in the input bit-width. The computation of a desired bit-width is completed by selecting an appropriate number of branches that satisfy the original computational constraint. By fixing the weight bit-width, this approach substantially reduces quantization errors caused by switching weight bit-widths. Additionally, we introduce an amortization branch selection strategy to distribute quantization errors caused by switching activation bit-widths among branches to improve performance. Finally, we adopt an in-place distillation strategy that facilitates guidance between branches to further enhance MBQuant's performance. Extensive experiments demonstrate that MBQuant achieves significant performance gains compared to existing arbitrary bit-width quantization methods. Code is at https://github.com/zysxmu/MultiQuant.