mlsanityData to 7 Oct 2026

HPTQ: Hardware-Friendly Post Training Quantization

arXiv 2109.09113 ↗First posted 19 Sep 2021cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Neural network quantization enables the deployment of models on edge devices. An essential requirement for their hardware efficiency is that the quantizers are hardware-friendly: uniform, symmetric, and with power-of-two thresholds. To the best of our knowledge, current post-training quantization methods do not support all of these constraints simultaneously. In this work, we introduce a hardware-friendly post training quantization (HPTQ) framework, which addresses this problem by synergistically combining several known quantization methods. We perform a large-scale study on four tasks: classification, object detection, semantic segmentation and pose estimation over a wide variety of network architectures. Our extensive experiments show that competitive results can be obtained under hardware-friendly constraints.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 42 of its 52 references that are in the map. First posted on arXiv 19 Sep 2021.

Builds on

42 of 52 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
30 more
  1. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  2. 2019Searching for MobileNetV3cited by 1,984
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  8. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  9. 2019Learned Step Size Quantizationcited by 604
  10. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  13. 2021A White Paper on Neural Network Quantizationcited by 453
  14. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  15. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  16. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  17. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 183
  18. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 180
  19. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 150
  20. 2019Loss Aware Post-training Quantizationcited by 94
  21. 2020Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programmingcited by 89
  22. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 87
  23. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  24. 2020Post-Training Piecewise Linear Quantization for Deep Neural Networkscited by 77
  25. 2018Value-aware Quantization for Training and Inference of Neural Networkscited by 49
  26. 2019Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizationcited by 45
  27. 2020HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNscited by 43
  28. 2019Fighting Quantization Bias With Biascited by 30
  29. 2018Quantization for Rapid Deployment of Deep Neural Networkscited by 20
  30. 2019Simple and Lightweight Human Pose Estimationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 2; 2026: 2.

9 papers.

  1. 2022Make RepVGG Greater Again: A Quantization-aware Approachcited by 21
  2. 2022Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementationcited by 6
  3. 2025PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applicationscited by 6
  4. 2023EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimizationcited by 5
  5. 2024Data Generation for Hardware-Friendly Post-Training Quantizationcited by 2
  6. 2024Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environmentcited by 1
  7. 2025EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devicescited by 1
  8. 2026PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentationcited by 1
  9. 2026IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computingcited by 0