# Enhancing Generalization in Data-free Quantization via Mixup-class Prompting

arXiv: https://arxiv.org/abs/2507.21947 · HTML: https://mlsanity.com/paper/2507.21947/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers](https://mlsanity.com/paper/2212.08254/) (2022)
- [Scaling Laws of Synthetic Images for Model Training ... for Now](https://mlsanity.com/paper/2312.04567/) (2023)
- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [PD-Quant: Post-Training Quantization based on Prediction Difference Metric](https://mlsanity.com/paper/2212.07048/) (2022)
- [Learning Vision from Models Rivals Learning Vision from Data](https://mlsanity.com/paper/2312.17742/) (2023)
- [ResizeMix: Mixing Data with Preserved Object Information and True Labels](https://mlsanity.com/paper/2012.11101/) (2020)
- [On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning](https://mlsanity.com/paper/1902.00621/) (2019)
- [Patch Similarity Aware Data-Free Quantization for Vision Transformers](https://mlsanity.com/paper/2203.02250/) (2022)
- [FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization](https://mlsanity.com/paper/2306.00317/) (2023)
- [Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples](https://mlsanity.com/paper/2111.02625/) (2021)
- [Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model](https://mlsanity.com/paper/2403.19600/) (2024)
- [MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing](https://mlsanity.com/paper/2011.09899/) (2020)
- [Adaptive Data-Free Quantization](https://mlsanity.com/paper/2303.06869/) (2023)
- [Genie: Show Me the Data for Quantization](https://mlsanity.com/paper/2212.04780/) (2022)
- [MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity](https://mlsanity.com/paper/2407.20021/) (2024)
- [Schr"odinger's Bat: Diffusion Models Sometimes Generate Polysemous Words in Superposition](https://mlsanity.com/paper/2211.13095/) (2022)
- [GenQ: Quantization in Low Data Regimes with Generative Synthetic Data](https://mlsanity.com/paper/2312.05272/) (2023)

## Built on by (most cited first, 1 of 1)

- [Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation](https://mlsanity.com/paper/2602.18861/) (2026)

## Abstract (arXiv)

Post-training quantization (PTQ) improves efficiency but struggles with limited calibration data, especially under privacy constraints. Data-free quantization (DFQ) mitigates this by generating synthetic images using generative models such as generative adversarial networks (GANs) and text-conditioned latent diffusion models (LDMs), while applying existing PTQ algorithms. However, the relationship between generated synthetic images and the generalizability of the quantized model during PTQ remains underexplored. Without investigating this relationship, synthetic images generated by previous prompt engineering methods based on single-class prompts suffer from issues such as polysemy, leading to performance degradation. We propose mixup-class prompt, a mixup-based text prompting strategy that fuses multiple class labels at the text prompt level to generate diverse, robust synthetic data. This approach enhances generalization, and improves optimization stability in PTQ. We provide quantitative insights through gradient norm and generalization error analysis. Experiments on convolutional neural networks (CNNs) and vision transformers (ViTs) show that our method consistently outperforms state-of-the-art DFQ methods like GenQ. Furthermore, it pushes the performance boundary in extremely low-bit scenarios, achieving new state-of-the-art accuracy in challenging 2-bit weight, 4-bit activation (W2A4) quantization.