Papers › Generative Low-bitwidth Data Free Quantization
Generative Low-bitwidth Data Free Quantization
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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