Data Free Quantization
13 papers with code • 2 benchmarks • 1 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
Benchmarks
These leaderboards are used to track progress in Data Free Quantization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Data Free Quantization models and implementations
CIFAR-100
Most implemented papers
Data-Free Quantization Through Weight Equalization and Bias Correction
This improves quantization accuracy performance, and can be applied to many common computer vision architectures with a straight forward API call.
ZeroQ: A Novel Zero Shot Quantization Framework
amirgholami/ZeroQ
•
•
CVPR 2020
Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0. 5\% of one epoch training time of ResNet50 on ImageNet).
Generative Low-bitwidth Data Free Quantization
More critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
iamkanghyunchoi/qimera
•
•
NeurIPS 2021
We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries.
Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
htqin/dsg
•
•
We first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics experimentally exhibit severe homogenization at distribution and sample levels.
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
clevercool/SQuant
•
•
ICLR 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.
Patch Similarity Aware Data-Free Quantization for Vision Transformers
zkkli/psaq-vit
•
•
The above insights guide us to design a relative value metric to optimize the Gaussian noise to approximate the real images, which are then utilized to calibrate the quantization parameters.
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
iamkanghyunchoi/ait
•
•
CVPR 2022
To deal with the performance drop induced by quantization errors, a popular method is to use training data to fine-tune quantized networks.
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
zkkli/psaq-vit
•
•
In this paper, we propose PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT.
Genie: Show Me the Data for Quantization
SamsungLabs/Genie
•
•
CVPR 2023
We also propose a post-training quantization algorithm to enhance the performance of quantized models.
