mlsanityData to 7 Oct 2026

F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

arXiv 2202.05239 ↗First posted 10 Feb 2022cs.CV cs.AI cs.ARcited by 26

Not on the map. Why?

Abstract (arXiv)

Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multiplication. To derive our method, we first discuss the advantages of fixed-point multiplication with different formats of fixed-point numbers and study the statistical behavior of the associated fixed-point numbers. Second, based on the statistical and algorithmic analysis, we apply different fixed-point formats for weights and activations of different layers. We introduce a novel algorithm to automatically determine the right format for each layer during training. Third, we analyze a previous quantization algorithm -- parameterized clipping activation (PACT) -- and reformulate it using fixed-point arithmetic. Finally, we unify the recently proposed method for quantization fine-tuning and our fixed-point approach to show the potential of our method. We verify F8Net on ImageNet for MobileNet V1/V2 and ResNet18/50. Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 59 of its 86 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

59 of 86 references.

References · 59

  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  6. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  7. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  8. 2019Learned Step Size Quantizationcited by 604
  9. 2018Rethinking the Value of Network Pruningcited by 595
  10. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  11. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  12. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
38 more
  1. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
  2. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  3. 2021A White Paper on Neural Network Quantizationcited by 453
  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. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  8. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  9. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  10. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  11. 2016Trained Ternary Quantizationcited by 203
  12. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  13. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 183
  14. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 180
  15. 2015Fixed Point Quantization of Deep Convolutional Networkscited by 141
  16. 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 115
  17. 2020Degree-Quant: Quantization-Aware Training for Graph Neural Networkscited by 93
  18. 2020Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programmingcited by 89
  19. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 87
  20. 2019Towards Unified INT8 Training for Convolutional Neural Networkcited by 77
  21. 2020Post-Training Piecewise Linear Quantization for Deep Neural Networkscited by 77
  22. 2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 77
  23. 2019AdaBits: Neural Network Quantization with Adaptive Bit-Widthscited by 63
  24. 2018Towards Understanding Regularization in Batch Normalizationcited by 56
  25. 2020FracBits: Mixed Precision Quantization via Fractional Bit-Widthscited by 53
  26. 2021Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?cited by 52
  27. 2020A Statistical Framework for Low-bitwidth Training of Deep Neural Networkscited by 51
  28. 2017WRPN: Wide Reduced-Precision Networkscited by 49
  29. 2018Value-aware Quantization for Training and Inference of Neural Networkscited by 49
  30. 2020HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNscited by 43
  31. 2020Searching for Low-Bit Weights in Quantized Neural Networkscited by 43
  32. 2019AtomNAS: Fine-Grained End-to-End Neural Architecture Searchcited by 40
  33. 2021Teachers Do More Than Teach: Compressing Image-to-Image Modelscited by 37
  34. 2021OMPQ: Orthogonal Mixed Precision Quantizationcited by 37
  35. 2020High-Capacity Expert Binary Networkscited by 34
  36. 2020A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutionscited by 32
  37. 2021Distribution Adaptive INT8 Quantization for Training CNNscited by 27
  38. 2020FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Trainingcited by 23

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 8; 2025: 6.

26 papers.

Sort:

By area:

  1. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  2. 2022The case for 4-bit precision: k-bit Inference Scaling Lawscited by 247
  3. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  4. 2023Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scalingcited by 62
  5. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  6. 2023A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platformscited by 21
  7. 2023Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantizationcited by 20
  8. 2022To update or not to update? Neurons at equilibrium in deep modelscited by 13
  9. 2025Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantizationcited by 13
  10. 2022Is Integer Arithmetic Enough for Deep Learning Training?cited by 11
  11. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  12. 2024Designing Large Foundation Models for Efficient Training and Inference: A Surveycited by 7
14 more
  1. 2025Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representationcited by 6
  2. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 6
  3. 2024Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approachcited by 5
  4. 2024SoD2: Statically Optimizing Dynamic Deep Neural Networkcited by 4
  5. 2024BOLD: Boolean Logic Deep Learningcited by 3
  6. 2024On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmeticcited by 3
  7. 2023Boolean Variation and Boolean Logic BackPropagationcited by 2
  8. 2024MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUscited by 2
  9. 2023Ultra-low Precision Multiplication-free Training for Deep Neural Networkscited by 1
  10. 2023Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environmentscited by 1
  11. 2025FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Reviewcited by 1
  12. 2025Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Accelerationcited by 1
  13. 2023RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architecturescited by 0
  14. 2024ISQuant: apply squant to the real deploymentcited by 0