Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

methodology-4

Data Free Quantization

3260 papers • 126 benchmarks • 313 datasets

Data Free Quantization is a technique to achieve a highly accurate quantized model without accessing any training data. Source: Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in data-free-quantization-9

Trend

Dataset

Best Model

Actions

CIFAR10

CIFAR10

CIFAR-100

CIFAR-100

Libraries

i

Use these libraries to find data-free-quantization-9 models and implementations

iamkanghyunchoi/ait

3 papers 29

Datasets

CIFAR-100

Subtasks

No subtasks available.

Most implemented papers

Data-Free Quantization Through Weight Equalization and Bias Correction

M. Welling, Markus Nagel, M. V. Baalen, Tijmen Blankevoort•Mon Jun 10 2019

This work introduces a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection, and achieves near-original model performance on common computer vision architectures and tasks.

580

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

ZeroQ: A Novel Zero Shot Quantization Framework

Z. Yao, A. Gholami, K. Keutzer, Michael W. Mahoney, Zhen Dong, Yaohui Cai•Wed Jan 01 2020

THE AUTHORS' enables mixed-precision quantization without any access to the training or validation data, and it can finish the entire quantization process in less than 30s, which is very low computational overhead.

462 0

Generative Low-bitwidth Data Free Quantization

Mingkui Tan, Bohan Zhuang, Shoukai Xu, Haokun Li, Jing Liu, Jiezhang Cao, Chuangrun Liang•Fri Mar 06 2020

This paper proposes a knowledge matching generator to produce meaningful fake data by exploiting classification boundary knowledge and distribution information in the pre-trained model with much higher accuracy on 4-bit quantization than the existing data free quantization method.

148 0

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Jinho Lee•Wed Nov 03 2021

Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples and uses an additional disentanglement mapping layer and extracting information from the full-precision model to better reflect the original distribution is proposed.

80 0

Diverse Sample Generation: Pushing the Limit of Generative Data-Free Quantization

Jiwen Lu, Xianglong Liu, Haotong Qin, Jiakai Wang, Yifu Ding, Xiangguo Zhang•Tue Aug 31 2021

This paper presents a generic Diverse Sample Generation (DSG) scheme for the generative data-free quantization, to mitigate detrimental homogenization and strengthens the loss impact of the specific BN layers for different samples and inhibit the correlation among samples in the generation process.

93 0

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Fan Yang, Yunxin Liu, Cong Guo, Yuxian Qiu, Jingwen Leng, Xiaotian Gao, Chen Zhang, Yuhao Zhu, Minyi Guo•Sun Feb 13 2022

This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements, and proposes a novel data-free optimization objective in the discrete domain, minimizing Constrained Absolute Sum of Error.

86 0

Patch Similarity Aware Data-Free Quantization for Vision Transformers

Zhikai Li, Liping Ma, Mengjuan Chen, Junrui Xiao, Qingyi Gu•Thu Mar 03 2022

This paper proposes PSAQ-ViT, a Patch Similarity Aware data-free Quantization framework for Vision Transformers, to enable the generation of "realistic" samples based on the vision transformer's unique properties for calibrating the quantization parameters.

70 0

It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher

Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Hye Yoon Lee, Joonsang Yu, Jinho Lee•Wed Mar 30 2022

AIT is proposed, a simple yet powerful technique for zero-shot quantization, which addresses the aforementioned two problems in the following way: AIT uses a KL distance loss only without a cross-entropy loss, and manipulates gradients to guarantee that a certain portion of weights are properly updated after crossing the rounding thresholds.

36 0

Genie: Show Me the Data for Quantization

Yongkweon Jeon, Chungman Lee, Ho-Young Kim•Thu Dec 08 2022

A post-training quantization scheme for zero-shot quantization that produces high-quality quantized networks within a few hours and a post- training quantization algorithm to enhance the performance of quantized models are introduced that can bridge the gap between zero- shot and few- shot quantization while significantly improving the quantization performance compared to that of existing approaches.

20 0

Adding a benchmark result helps the community track progress.

Data Free Quantization | State-of-the-Art