# CSMPQ:Class Separability Based Mixed-Precision Quantization

arXiv: https://arxiv.org/abs/2212.10220 · HTML: https://mlsanity.com/paper/2212.10220/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 19 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 18 of 18)

- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.00090/) (2018)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [HAWQV3: Dyadic Neural Network Quantization](https://mlsanity.com/paper/2011.10680/) (2020)
- [FracBits: Mixed Precision Quantization via Fractional Bit-Widths](https://mlsanity.com/paper/2007.02017/) (2020)
- [Value-aware Quantization for Training and Inference of Neural Networks](https://mlsanity.com/paper/1804.07802/) (2018)
- [HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs](https://mlsanity.com/paper/2007.09952/) (2020)
- [Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization](https://mlsanity.com/paper/2007.10026/) (2020)
- [ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks](https://mlsanity.com/paper/1811.01704/) (2018)
- [One Weight Bitwidth to Rule Them All](https://mlsanity.com/paper/2008.09916/) (2020)

## Abstract (arXiv)

Mixed-precision quantization has received increasing attention for its capability of reducing the computational burden and speeding up the inference time. Existing methods usually focus on the sensitivity of different network layers, which requires a time-consuming search or training process. To this end, a novel mixed-precision quantization method, termed CSMPQ, is proposed. Specifically, the TF-IDF metric that is widely used in natural language processing (NLP) is introduced to measure the class separability of layer-wise feature maps. Furthermore, a linear programming problem is designed to derive the optimal bit configuration for each layer. Without any iterative process, the proposed CSMPQ achieves better compression trade-offs than the state-of-the-art quantization methods. Specifically, CSMPQ achieves 73.03% Top-1 acc on ResNet-18 with only 59G BOPs for QAT, and 71.30% top-1 acc with only 1.5Mb on MobileNetV2 for PTQ.