mlsanityData to 7 Oct 2026

Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation

arXiv 2602.18861 ↗First posted 21 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly optimize over the entire set of all layers and inter-block dependencies without any labeled data, scaling effectively with the number of samples and completing in just one hour on a single GPU for ViT-small. We achieve state-of-the-art W4A4 and W3A3 accuracies on ImageNet and, to the best of our knowledge, the first PTQ results that maintain strong accuracy on ViT, DeiT, and Swin-T models under extremely low-bit settings (W1.58A8), demonstrating the potential for efficient edge deployment. Furthermore, we introduce a data-free calibration strategy that synthesizes diverse, label-free samples using Stable Diffusion Turbo guided by learned multi-mode prompts. By encouraging diversity in both the learned prompt embeddings and the generated image features, our data-free approach achieves performance on par with real-data ImageNet calibration and surpasses simple text-prompt baselines such as "a <adjective> photo of <adjective> <cls>".

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 31 references that are in the map. First posted on arXiv 21 Feb 2026.

Builds on

29 of 31 references.

References · 29

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  4. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  5. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  6. 2023Adversarial Diffusion Distillationcited by 741
  7. 2019Learned Step Size Quantizationcited by 604
  8. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  9. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  10. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  11. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 403
  12. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
17 more
  1. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  2. 2021Post-Training Quantization for Vision Transformercited by 274
  3. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  4. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  5. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  6. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 106
  7. 2020Generative Low-bitwidth Data Free Quantizationcited by 87
  8. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  9. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 55
  10. 2022PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformerscited by 42
  11. 2023CBQ: Cross-Block Quantization for Large Language Modelscited by 34
  12. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 28
  13. 2024CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTscited by 17
  14. 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformerscited by 17
  15. 2025FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximationcited by 16
  16. 2023GenQ: Quantization in Low Data Regimes with Generative Synthetic Datacited by 8
  17. 2025Enhancing Generalization in Data-free Quantization via Mixup-class Promptingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformers
  2. 2024VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
  3. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  4. 2026Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
  5. 2026Amortized-Precision Quantization for Early-Exit Vision Transformers
  6. 2025ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
  7. 2023Learned Thresholds Token Merging and Pruning for Vision Transformers
  8. 2026OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers