mlsanityData to 14 Oct 2026

Ternary Quantization: A Survey

arXiv 2303.01505 ↗First posted 2 Mar 2023cs.LG cs.AI cs.CCcited by 2

Not on the map. Why?

Abstract (arXiv)

Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to compress neural network models with faster inference and higher accuracy. Pruning and quantization are mainstream methods to this end. During model quantization, converting individual float values of layer weights to low-precision ones can substantially reduce the computational overhead and improve the inference speed. Many quantization methods have been studied, for example, vector quantization, low-bit quantization, and binary/ternary quantization. This survey focuses on ternary quantization. We review the evolution of ternary quantization and investigate the relationships among existing ternary quantization methods from the perspective of projection function and optimization methods.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

41 of 65 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  8. 2015Deep Learning with Limited Numerical Precisioncited by 376
  9. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  10. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
  11. 2016Trained Ternary Quantizationcited by 208
  12. 2016Ternary Weight Networkscited by 204
29 more
  1. 2020Training with Quantization Noise for Extreme Model Compressioncited by 145
  2. 2017Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracycited by 101
  3. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 70
  4. 2017Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMcited by 61
  5. 2018ProxQuant: Quantized Neural Networks via Proximal Operatorscited by 59
  6. 2017WRPN: Wide Reduced-Precision Networkscited by 51
  7. 2015Neural Networks with Few Multiplicationscited by 48
  8. 2020Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4MLcited by 42
  9. 2015Resiliency of Deep Neural Networks under Quantizationcited by 35
  10. 2016Ternary Neural Networks for Resource-Efficient AI Applicationscited by 33
  11. 2018Loss-aware Weight Quantization of Deep Networkscited by 31
  12. 2017Learning Discrete Weights Using the Local Reparameterization Trickcited by 29
  13. 2018SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networkscited by 24
  14. 2020BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activationscited by 23
  15. 2017Ternary Neural Networks with Fine-Grained Quantizationcited by 17
  16. 2019RTN: Reparameterized Ternary Networkcited by 9
  17. 2016Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detectioncited by 8
  18. 2019Adaptive Binary-Ternary Quantizationcited by 8
  19. 2020DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networkscited by 8
  20. 2019TiM-DNN: Ternary in-Memory accelerator for Deep Neural Networkscited by 7
  21. 2020FATNN: Fast and Accurate Ternary Neural Networkscited by 7
  22. 2015Rounding Methods for Neural Networks with Low Resolution Synaptic Weightscited by 5
  23. 2016Fixed-point Factorized Networkscited by 5
  24. 2018Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracycited by 4
  25. 2022Hyperspherical Quantization: Toward Smaller and More Accurate Modelscited by 4
  26. 2019Cluster Regularized Quantization for Deep Networks Compressioncited by 3
  27. 2020RPR: Random Partition Relaxation for Training; Binary and Ternary Weight Neural Networkscited by 2
  28. 2022Soft Threshold Ternary Networkscited by 2
  29. 2020Memory and Computation-Efficient Kernel SVM via Binary Embedding and Ternary Model Coefficientscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Tequila: Trapping-free Ternary Quantization for Large Language Modelscited by 9
  2. 2026Big2Small: A Unifying Neural Network Framework for Model Compressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Designing strong baselines for ternary neural network quantization through support and mass equalization
  2. 2021Pruning Ternary Quantization
  3. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  4. 2026CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
  5. 2026Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
  6. 2025Ternarization of Vision Language Models for use on edge devices
  7. 2022Vertical Layering of Quantized Neural Networks for Heterogeneous Inference
  8. 2021Neural Network Quantization for Efficient Inference: A Survey