mlsanityData to 7 Oct 2026

Quantization Range Estimation for Convolutional Neural Networks

arXiv 2510.04044 ↗First posted 5 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Post-training quantization for reducing the storage of deep neural network models has been demonstrated to be an effective way in various tasks. However, low-bit quantization while maintaining model accuracy is a challenging problem. In this paper, we present a range estimation method to improve the quantization performance for post-training quantization. We model the range estimation into an optimization problem of minimizing quantization errors by layer-wise local minima. We prove this problem is locally convex and present an efficient search algorithm to find the optimal solution. We propose the application of the above search algorithm to the transformed weights space to do further improvement in practice. Our experiments demonstrate that our method outperforms state-of-the-art performance generally on top-1 accuracy for image classification tasks on the ResNet series models and Inception-v3 model. The experimental results show that the proposed method has almost no loss of top-1 accuracy in 8-bit and 6-bit settings for image classifications, and the accuracy of 4-bit quantization is also significantly improved. The code is available at https://github.com/codeiscommitting/REQuant.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 5 Oct 2025.

Builds on

34 of 49 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  6. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  7. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  8. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  9. 2021A White Paper on Neural Network Quantizationcited by 453
  10. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  11. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  12. 2018Paraphrasing Complex Network: Network Compression via Factor Transfercited by 255
22 more
  1. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 250
  2. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  3. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  4. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 143
  5. 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 115
  6. 2015Convolutional neural networks with low-rank regularizationcited by 102
  7. 2017Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracycited by 100
  8. 2016Convolutional Neural Networks using Logarithmic Data Representationcited by 97
  9. 2017Towards Effective Low-bitwidth Convolutional Neural Networkscited by 76
  10. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
  11. 2024Compressing Large Language Models using Low Rank and Low Precision Decompositioncited by 58
  12. 2022Mixed-Precision Neural Network Quantization via Learned Layer-wise Importancecited by 53
  13. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 51
  14. 2019Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understandingcited by 37
  15. 2020The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understandingcited by 28
  16. 2017Towards End-to-End Speech Recognition with Deep Convolutional Neural Networkscited by 24
  17. 2023PowerQuant: Automorphism Search for Non-Uniform Quantizationcited by 20
  18. 2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratchcited by 20
  19. 2020Neural Network Compression Framework for fast model inferencecited by 18
  20. 2019Filter Pruning by Switching to Neighboring CNNs with Good Attributescited by 15
  21. 2016Very Deep Convolutional Networks for Text Classificationcited by 12
  22. 2025Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradientscited by 2

Built on by

Not cited yet.