AI Paper Atlas

Research map / Architectures and efficiency / Quantization

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

Haotong Qin, Yifu Ding, Xiangguo Zhang, Jiakai Wang, Xianglong Liu, Jiwen Lu

TPAMI 2023 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 122 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Slack Distribution Alignment (SDA) (ablation)ZeroQ vanilla · ImageNet ResNet18 W4A4 PTQtop-1 accuracy: 26.04 -> 33.39Improved
add Slack Distribution Alignment (SDA) (ablation)GDFQ vanilla · ImageNet ResNet18 W4A4 QATtop-1 accuracy: 60.52 -> 61.08Improved
set slack epsilon to 1 instead of 0.9 (ablation)SDA in PTQ · ImageNet ResNet18 W4A4 PTQtop-1 accuracy: drops 3.61%Hurt
set slack epsilon to 1 instead of 0.9 (ablation)SDA in QAT · ImageNet ResNet18 W4A4 QATtop-1 accuracy: drops 0.02%Hurt
add Layerwise Sample Enhancement (LSE) (ablation)ZeroQ vanilla · ImageNet ResNet18 W4A4 PTQtop-1 accuracy: 26.04 -> 27.12Improved
add Layerwise Sample Enhancement (LSE) (ablation)GDFQ vanilla · ImageNet ResNet18 W4A4 QATtop-1 accuracy: 60.52 -> 60.71Improved
add Sample Correlation Inhibition (SCI) (ablation)ZeroQ vanilla · ImageNet ResNet18 W4A4 PTQtop-1 accuracy: 26.04 -> 39.53Improved
add Sample Correlation Inhibition (SCI) (ablation)GDFQ vanilla · ImageNet ResNet18 W4A4 QATtop-1 accuracy: 60.52 -> 60.92Improved
combine SDA, LSE and SCI (full DSG) (ablation)GDFQ vanilla · ImageNet ResNet18 W4A4 QATtop-1 accuracy: 60.52 -> 62.18Improved
combine SDA, LSE and SCI (full DSG) (ablation)ZeroQ vanilla · ImageNet ResNet18 W4A4 PTQtop-1 accuracy: 26.04 -> 39.90Improved
calibrate with DSG synthetic data instead of real dataResNet20 CIFAR10 PTQ · CIFAR10 W4A4top-1 accuracy: 87.38 -> 87.79Improved
replace ZeroQ synthetic data with DSG data and SQuant calibrationResNet18 · ImageNet PTQ W4A4top-1 accuracy: 65.22 -> 66.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy