# Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

arXiv: https://arxiv.org/abs/2111.02625 · HTML: https://mlsanity.com/paper/2111.02625/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Latent Space Oddity: on the Curvature of Deep Generative Models](https://mlsanity.com/paper/1710.11379/) (2017)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Data-Free Knowledge Distillation for Deep Neural Networks](https://mlsanity.com/paper/1710.07535/) (2017)

## Built on by (most cited first, 30 of 40)

- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers](https://mlsanity.com/paper/2209.05687/) (2022)
- [Adaptive Data-Free Quantization](https://mlsanity.com/paper/2303.06869/) (2023)
- [Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning](https://mlsanity.com/paper/2308.07209/) (2023)
- [It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher](https://mlsanity.com/paper/2203.17008/) (2022)
- [Genie: Show Me the Data for Quantization](https://mlsanity.com/paper/2212.04780/) (2022)
- [CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs](https://mlsanity.com/paper/2407.05266/) (2024)
- [Hard Sample Matters a Lot in Zero-Shot Quantization](https://mlsanity.com/paper/2303.13826/) (2023)
- [Rethinking Data-Free Quantization as a Zero-Sum Game](https://mlsanity.com/paper/2302.09572/) (2023)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning](https://mlsanity.com/paper/2307.00498/) (2023)
- [MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity](https://mlsanity.com/paper/2407.20021/) (2024)
- [A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization](https://mlsanity.com/paper/2307.12659/) (2023)
- [GenQ: Quantization in Low Data Regimes with Generative Synthetic Data](https://mlsanity.com/paper/2312.05272/) (2023)
- [Zero-shot Quantization: A Comprehensive Survey](https://mlsanity.com/paper/2505.09188/) (2025)
- [Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy](https://mlsanity.com/paper/2208.13648/) (2022)
- [Dataset Size Recovery from LoRA Weights](https://mlsanity.com/paper/2406.19395/) (2024)
- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [Radio: Rate-Distortion Optimization for Large Language Model Compression](https://mlsanity.com/paper/2505.03031/) (2025)
- [Long-Range Zero-Shot Generative Deep Network Quantization](https://mlsanity.com/paper/2211.06816/) (2022)
- [Robustness-Guided Image Synthesis for Data-Free Quantization](https://mlsanity.com/paper/2310.03661/) (2023)
- [Knowledge Distillation Detection for Open-weights Models](https://mlsanity.com/paper/2510.02302/) (2025)
- [Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization](https://mlsanity.com/paper/2205.00179/) (2022)
- [Efficient Adaptive Activation Rounding for Post-Training Quantization](https://mlsanity.com/paper/2208.11945/) (2022)
- [Redistribution of Weights and Activations for AdderNet Quantization](https://mlsanity.com/paper/2212.10200/) (2022)
- [Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers](https://mlsanity.com/paper/2412.16553/) (2024)
- [ACQ: Improving Generative Data-free Quantization Via Attention Correction](https://mlsanity.com/paper/2301.07266/) (2023)
- [Foundations of Large Language Model Compression -- Part 1: Weight Quantization](https://mlsanity.com/paper/2409.02026/) (2024)
- [Data Generation for Hardware-Friendly Post-Training Quantization](https://mlsanity.com/paper/2410.22110/) (2024)
- [Infrared Domain Adaptation with Zero-Shot Quantization](https://mlsanity.com/paper/2408.13925/) (2024)

## Abstract (arXiv)

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to maintain the accuracy of the full-precision models, which is often infeasible in real-world scenarios for security and privacy issues. A popular approach to perform quantization without access to the original data is to use synthetically generated samples, based on batch-normalization statistics or adversarial learning. However, the drawback of such approaches is that they primarily rely on random noise input to the generator to attain diversity of the synthetic samples. We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries. To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. For the superposed embeddings to better reflect the original distribution, we also propose using an additional disentanglement mapping layer and extracting information from the full-precision model. The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization. Code is available at https://github.com/iamkanghyunchoi/qimera.