Papers › Generative Low-bitwidth Data Free Quantization

Generative Low-bitwidth Data Free Quantization

7 Mar 2020ECCV 2020 8arXiv:2003.03603archive 2025-07-28

Shoukai Xu, Haokun Li, Bohan Zhuang, Jing Liu, JieZhang Cao, Chuangrun Liang, Mingkui Tan

Neural network quantization is an effective way to compress deep models and improve their execution latency and energy efficiency, so that they can be deployed on mobile or embedded devices. Existing quantization methods require original data for calibration or fine-tuning to get better performance. However, in many real-world scenarios, the data may not be available due to confidential or private issues, thereby making existing quantization methods not applicable. Moreover, due to the absence of original data, the recently developed generative adversarial networks (GANs) cannot be applied to generate data. Although the full-precision model may contain rich data information, such information alone is hard to exploit for recovering the original data or generating new meaningful data. In this paper, we investigate a simple-yet-effective method called Generative Low-bitwidth Data Free Quantization (GDFQ) to remove the data dependence burden. Specifically, we propose a knowledge matching generator to produce meaningful fake data by exploiting classification boundary knowledge and distribution information in the pre-trained model. With the help of generated data, we can quantize a model by learning knowledge from the pre-trained model. Extensive experiments on three data sets demonstrate the effectiveness of our method. More critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method. Code is available at https://github.com/xushoukai/GDFQ.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xushoukai/GDFQ officialmentioned in papermentioned on GitHubpytorch report
iamkanghyunchoi/ait mentioned on GitHubpytorch report
ricky40403/GDFQ mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data Free QuantizationQuantization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data Free Quantization CIFAR-100 ResNet-20 CIFAR-100 CIFAR-100 W4A4 Top-1 Accuracy 43.12 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR-100 ResNet-20 CIFAR-100 CIFAR-100 W5A5 Top-1 Accuracy 64.03 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR-100 ResNet-20 CIFAR-100 CIFAR-100 W6A6 Top-1 Accuracy 68.63 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR-100 ResNet-20 CIFAR-100 CIFAR-100 W8A8 Top-1 Accuracy 70.29 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR10 ResNet-20 CIFAR-10 CIFAR-10 W4A4 Top-1 Accuracy 85.20 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR10 ResNet-20 CIFAR-10 CIFAR-10 W5A5 Top-1 Accuracy 92.39 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR10 ResNet-20 CIFAR-10 CIFAR-10 W6A6 Top-1 Accuracy 93.38 #2 of 3 Archive leaderboard report
Data Free Quantization CIFAR10 ResNet-20 CIFAR-10 CIFAR-10 W8A8 Top-1 Accuracy 93.92 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections