AI Paper Atlas

Research map / Architectures and efficiency / Quantization

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data

Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda

ECCV 2024 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 9 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
use GenQ text-to-image synthetic data instead of Genie-D inversion data (MobileNet-b W2A4)BRECQ PTQ · ImageNet data-free PTQ W2A4top-1 accuracy (%): 38.01 -> 47.31Improved
use GenQ data instead of Genie-D on ResNet architecturesBRECQ PTQ · ImageNet data-free PTQ W4A4top-1 accuracy (%): 75.35 -> 75.47 (ResNet-50)No clear effect
use GenQ synthetic data instead of TexQ GAN data for W3A3 QATResNet-50 QAT · ImageNet data-free QAT W3A3top-1 accuracy (%): 25.27 -> 73.99Improved
add GenQ data-scarce synthetic data to 1k real imagesResNet-50 W3A3 QAT · ImageNet 1-shottop-1 accuracy (%): 68.88% with 1k real, similar to QAT with 300x more dataImproved
increase number of synthetic images for PTQ (ablation)GenQ · ResNet-50 W2A4 PTQtop-1 accuracy (%)Improved
increase energy-score filtering ratio (ablation)GenQ · ResNet-18 W2A4 PTQtop-1 accuracy (%)Improved
increase BN-sensitivity filtering ratio beyond 50% (ablation)GenQ · ResNet-18 W2A4 PTQtop-1 accuracy (%)Hurt
use text-to-image synthesis instead of image inversionsynthetic data generation · 1000 ImageNet imageslatency: 152 min -> 24 minImproved
use GenQ data synthesized on a different model for quantization (transfer)GenQ · cross-model PTQ W2A4top-1 accuracy (%): drop of 0.2-0.5% vs 0.6-33% for existing methodsNo clear effect

Later papers that compared with this method

1 later accepted paper reports GenQ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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