AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction

Yunshan Zhong, Huang You, Jiawei Hu, Yuxin Zhang, Rongrong Ji

TPAMI 2025 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 27 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 activation quantization error reduction (Aqer) (ablation)ERQ on calibration baseline · DeiT-S W4A4 ImageNettop-1 accuracy: 40.38 -> 70.96Improved
add weight quantization error reduction (Wqer) (ablation)ERQ on calibration baseline · DeiT-S W4A4 ImageNettop-1 accuracy: 40.38 -> 50.92Improved
add Wqer on top of Aqer (ablation)ERQ · DeiT-S W4A4 ImageNettop-1 accuracy: 70.96 -> 74.35Improved
add Reparameterization Initialization to Aqer (ablation)Aqer · DeiT-S W4A4 ImageNettop-1 accuracy: 50.92 -> 72.95Improved
add Ridge Regression to Aqer (ablation)Aqer · DeiT-S W4A4 ImageNettop-1 accuracy: 50.92 -> 59.59Improved
add Dual Uniform Quantization to Wqer (ablation)Wqer · DeiT-S W4A4 ImageNettop-1 accuracy: 70.96 -> 73.03Improved
add Rounding Refinement to Wqer (ablation)Wqer · DeiT-S W4A4 ImageNettop-1 accuracy: 70.96 -> 71.80Improved
add Ridge Regression to Wqer (ablation)Wqer · DeiT-S W4A4 ImageNettop-1 accuracy: 70.96 -> 72.12Improved
increase Rounding Refinement k from 1 to 3 (ablation)Rounding Refinement · DeiT-S W4A4 ImageNettop-1 accuracy: 74.35 -> 73.79Hurt
use 5% of D_out as outlier channels instead of none (ablation)Dual Uniform Quantization · DeiT-S W4A4 ImageNettop-1 accuracy: 72.76 -> 74.35Improved
increase outlier channels from 5% to 20% of D_out (ablation)Dual Uniform Quantization · DeiT-S W4A4 ImageNettop-1 accuracy: 74.35 -> 73.26Hurt
raise maximum iterations T from 0 to 20 (ablation)Rounding Refinement · DeiT-S W4A4 ImageNettop-1 accuracy: 74.06 -> 74.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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