mlsanityData to 7 Oct 2026

PD-Quant: Post-Training Quantization based on Prediction Difference Metric

arXiv 2212.07048 ↗First posted 14 Dec 2022cs.CV eess.IVcited by 73

Not on the map. Why?

Abstract (arXiv)

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep neural networks, it can also introduce quantization noise and reduce prediction accuracy, especially in extremely low-bit settings. How to determine the appropriate quantization parameters (e.g., scaling factors and rounding of weights) is the main problem facing now. Existing methods attempt to determine these parameters by minimize the distance between features before and after quantization, but such an approach only considers local information and may not result in the most optimal quantization parameters. We analyze this issue and ropose PD-Quant, a method that addresses this limitation by considering global information. It determines the quantization parameters by using the information of differences between network prediction before and after quantization. In addition, PD-Quant can alleviate the overfitting problem in PTQ caused by the small number of calibration sets by adjusting the distribution of activations. Experiments show that PD-Quant leads to better quantization parameters and improves the prediction accuracy of quantized models, especially in low-bit settings. For example, PD-Quant pushes the accuracy of ResNet-18 up to 53.14% and RegNetX-600MF up to 40.67% in weight 2-bit activation 2-bit. The code is released at https://github.com/hustvl/PD-Quant.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 14 Dec 2022.

Builds on

49 of 64 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  9. 2020Knowledge Distillation: A Surveycited by 1,578
  10. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  11. 2020Designing Network Design Spacescited by 954
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
37 more
  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2019Learned Step Size Quantizationcited by 604
  3. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  4. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
  5. 2018Rethinking the Value of Network Pruningcited by 595
  6. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  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. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  10. 2021A White Paper on Neural Network Quantizationcited by 453
  11. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  12. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
  13. 2018Model compression via distillation and quantizationcited by 287
  14. 2021Post-Training Quantization for Vision Transformercited by 274
  15. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  16. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  17. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  18. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  19. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  20. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  21. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
  22. 2019Quantization Networkscited by 151
  23. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 150
  24. 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 115
  25. 2019Loss Aware Post-training Quantizationcited by 94
  26. 2020Generative Low-bitwidth Data Free Quantizationcited by 87
  27. 2020Post-Training Piecewise Linear Quantization for Deep Neural Networkscited by 77
  28. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  29. 2018Data augmentation instead of explicit regularizationcited by 62
  30. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  31. 2019The Knowledge Within: Methods for Data-Free Model Compressioncited by 54
  32. 2018Value-aware Quantization for Training and Inference of Neural Networkscited by 49
  33. 2021IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantizationcited by 43
  34. 2017Theory of Deep Learning III: explaining the non-overfitting puzzlecited by 32
  35. 2018Quantization for Rapid Deployment of Deep Neural Networkscited by 20
  36. 2022It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teachercited by 20
  37. 2022RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantizationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 28; 2025: 22; 2026: 13.

73 papers.

Sort:

By area:

  1. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformerscited by 77
  2. 2024WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains Morecited by 69
  3. 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibrationcited by 54
  4. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuningcited by 48
  5. 2023TinySAM: Pushing the Envelope for Efficient Segment Anything Modelcited by 33
  6. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  7. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  8. 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methodscited by 26
  9. 2024Quantization without Tearscited by 24
  10. 2024Towards Accurate Post-Training Quantization of Vision Transformers via Error Reductioncited by 23
  11. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Modelscited by 20
  12. 2023I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantizationcited by 19
38 more
  1. 2024I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Modelscited by 19
  2. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformerscited by 19
  3. 2023Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learningcited by 17
  4. 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformerscited by 17
  5. 2024LPViT: Low-Power Semi-structured Pruning for Vision Transformerscited by 15
  6. 2024Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attackscited by 14
  7. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  8. 2024COMQ: A Backpropagation-Free Algorithm for Post-Training Quantizationcited by 12
  9. 2025MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillationcited by 12
  10. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  11. 2025QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perceptioncited by 11
  12. 2024MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformercited by 10
  13. 2024IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Modelscited by 9
  14. 2023Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performancecited by 8
  15. 2023NUPES : Non-Uniform Post-Training Quantization via Power Exponent Searchcited by 7
  16. 2024Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalitiescited by 7
  17. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformerscited by 7
  18. 2025PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Modelscited by 7
  19. 2023EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimizationcited by 5
  20. 2024MetaAug: Meta-Data Augmentation for Post-Training Quantizationcited by 5
  21. 2024Temporal Feature Matters: A Framework for Diffusion Model Quantizationcited by 5
  22. 2024PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Modelscited by 5
  23. 2024Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsitycited by 5
  24. 2024PTQ4RIS: Post-Training Quantization for Referring Image Segmentationcited by 4
  25. 2024FP=xINT:Representing Neural Networks via Low-Bit Series Basis Functionscited by 4
  26. 2025Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Modelcited by 4
  27. 2023R2 Loss: Range Restriction Loss for Model Compression and Quantizationcited by 3
  28. 2024An Analysis on Quantizing Diffusion Transformerscited by 3
  29. 2025SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Modelcited by 3
  30. 2025MoQE: Improve Quantization Model performance via Mixture of Quantization Expertscited by 3
  31. 2025AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Modelscited by 3
  32. 2023Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metriccited by 2
  33. 2024An Edge AI System Based on FPGA Platform for Railway Fault Detectioncited by 2
  34. 2024Art and Science of Quantizing Large-Scale Models: A Comprehensive Overviewcited by 2
  35. 2024Data Generation for Hardware-Friendly Post-Training Quantizationcited by 2
  36. 2025Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Groupingcited by 2
  37. 2025LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformerscited by 2
  38. 2026Saliency-Aware Regularized Quantization Calibration for Large Language Modelscited by 2

50 most cited of 73 All 73 (JSON)