AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Jinho Lee

NeurIPS 2021 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 5 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 superposed embeddings (SE) (ablation)GDFQ · ImageNet ResNet-50 4w4atop-1 accuracy: 52.12 -> 64.09Improved
add superposed embeddings (SE) (ablation)GDFQ · CIFAR-100 ResNet-20 4w4atop-1 accuracy: 63.39 -> 64.55Improved
add disentanglement mapping (DM) to SE (ablation)GDFQ + SE · ImageNet ResNet-50 4w4atop-1 accuracy: 64.09 -> 66.06Improved
add disentanglement mapping (DM) to SE (ablation)GDFQ + SE · CIFAR-100 ResNet-20 4w4atop-1 accuracy: 64.55 -> 64.76No clear effect
add extracted embedding initialization (EEI) to SE (ablation)GDFQ + SE · CIFAR-100 ResNet-20 4w4atop-1 accuracy: 64.55 -> 65.23Improved
add DM and EEI together to SE (ablation)GDFQ + SE · ImageNet ResNet-50 4w4atop-1 accuracy: 66.06 -> 66.25Improved
freeze embeddings after extracted initialization (no training) (ablation)Qimera · ImageNet ResNet-50 4w4atop-1 accuracy: 66.25 -> 63.20Hurt
apply Mixup-style input mixing on GDFQ samplesGDFQ · ImageNet ResNet-50 4w4atop-1 accuracy: 52.12 -> 59.25Improved
apply Cutmix on GDFQ samplesGDFQ · CIFAR-100 ResNet-20 4w4atop-1 accuracy: 63.39 -> 62.74Hurt
lower generator noise sigma_z from 1.0 to 0.25 (ablation)GDFQ · ImageNet ResNet-50 4w4atop-1 accuracy: 52.12 -> 55.30Improved
raise generator noise sigma_z from 1.0 to 2.0 (ablation)GDFQ · ImageNet ResNet-50 4w4atop-1 accuracy: 52.12 -> 46.14Hurt
use 8 DM layers instead of 1 (ablation)Qimera · CIFAR-100 ResNet-20 4w4atop-1 accuracy: 65.10 -> 64.11Hurt

Later papers that compared with this method

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

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