mlsanityData to 7 Oct 2026

CSMPQ:Class Separability Based Mixed-Precision Quantization

arXiv 2212.10220 ↗First posted 20 Dec 2022cs.CVcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 19 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

18 of 19 references.

References · 18

  1. 2019Learned Step Size Quantizationcited by 604
  2. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  3. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  4. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  5. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  6. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  7. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  8. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  9. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  10. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
  11. 2021Network Quantization with Element-wise Gradient Scalingcited by 82
  12. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 59
6 more
  1. 2020FracBits: Mixed Precision Quantization via Fractional Bit-Widthscited by 53
  2. 2018Value-aware Quantization for Training and Inference of Neural Networkscited by 49
  3. 2020HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNscited by 43
  4. 2020Search What You Want: Barrier Panelty NAS for Mixed Precision Quantizationcited by 31
  5. 2018ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networkscited by 14
  6. 2020One Weight Bitwidth to Rule Them Allcited by 13

Built on by

Not cited yet.