mlsanityData to 14 Oct 2026

Zero-shot Quantization: A Comprehensive Survey

arXiv 2505.09188 ↗First posted 14 May 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Network quantization has proven to be a powerful approach to reduce the memory and computational demands of deep learning models for deployment on resource-constrained devices. However, traditional quantization methods often rely on access to training data, which is impractical in many real-world scenarios due to privacy, security, or regulatory constraints. Zero-shot Quantization (ZSQ) emerges as a promising solution, achieving quantization without requiring any real data. In this paper, we provide a comprehensive overview of ZSQ methods and their recent advancements. First, we provide a formal definition of the ZSQ problem and highlight the key challenges. Then, we categorize the existing ZSQ methods into classes based on data generation strategies, and analyze their motivations, core ideas, and key takeaways. Lastly, we suggest future research directions to address the remaining limitations and advance the field of ZSQ. To the best of our knowledge, this paper is the first in-depth survey on ZSQ.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

40 of 56 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  6. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  8. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  9. 2015Deep Learning with Limited Numerical Precisioncited by 376
  10. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  11. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
  12. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
28 more
  1. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  2. 2018Gradient Harmonized Single-stage Detectorcited by 114
  3. 2020Generative Low-bitwidth Data Free Quantizationcited by 88
  4. 2021Diversifying Sample Generation for Accurate Data-Free Quantizationcited by 63
  5. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 56
  6. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 55
  7. 2019The Knowledge Within: Methods for Data-Free Model Compressioncited by 54
  8. 2021Zero-shot Adversarial Quantizationcited by 44
  9. 2022Pruning has a disparate impact on model accuracycited by 44
  10. 2021IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantizationcited by 43
  11. 2021Qimera: Data-free Quantization with Synthetic Boundary Supporting Samplescited by 40
  12. 2020MixMix: All You Need for Data-Free Compression Are Feature and Data Mixingcited by 29
  13. 2023Adaptive Data-Free Quantizationcited by 26
  14. 2023Unified Data-Free Compression: Pruning and Quantization without Fine-Tuningcited by 23
  15. 2022It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teachercited by 20
  16. 2021AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compressioncited by 17
  17. 2022Genie: Show Me the Data for Quantizationcited by 17
  18. 2024CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTscited by 17
  19. 2023Hard Sample Matters a Lot in Zero-Shot Quantizationcited by 15
  20. 2024A Comprehensive Survey of Compression Algorithms for Language Modelscited by 15
  21. 2023Rethinking Data-Free Quantization as a Zero-Sum Gamecited by 13
  22. 2023Accurate Retraining-free Pruning for Pretrained Encoder-based Language Modelscited by 11
  23. 2023GenQ: Quantization in Low Data Regimes with Generative Synthetic Datacited by 8
  24. 2021A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statisticscited by 6
  25. 2023Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrievalcited by 6
  26. 2023Causal-DFQ: Causality Guided Data-free Network Quantizationcited by 6
  27. 2023Robustness-Guided Image Synthesis for Data-Free Quantizationcited by 4
  28. 2025AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 7
  2. 2025Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Modelscited by 5
  3. 2026Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compressioncited by 3
  4. 2025Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Informationcited by 2
  5. 2025CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Roundingcited by 1
  6. 2026Compute Only Once: UG-Separation for Efficient Large Recommendation Modelscited by 1
  7. 2025D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Modelscited by 0
  8. 2026Discriminative Score Function: Turning Pretrained Models into Functional Generative Priorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
  2. 2023Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
  3. 2025GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
  4. 2024Data Generation for Hardware-Friendly Post-Training Quantization
  5. 2025Sharpness-Aware Data Generation for Zero-shot Quantization
  6. 2022Long-Range Zero-Shot Generative Deep Network Quantization
  7. 2021Generative Zero-shot Network Quantization
  8. 2025ZOQO: Zero-Order Quantized Optimization