AI Paper Atlas

Research map / Architectures and efficiency / Quantization

UQ-ViT: Harmonizing Extreme Activations with Hardware-Friendly Uniform Quantization in Vision Transformers

Tao Jiang, Yucheng Jiang, Xiwen Yao, Gong Cheng, Junwei Han

AAAI 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 1 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 DeMax and NormQuant to uniform-quantized RepQ-ViT baseline (ablation)RepQ-ViT with uniform quantization · ImageNet W4/A4, DeiT-Stop-1 accuracy: 68.98 -> 72.13Improved
add DeMax and NormQuant to uniform-quantized RepQ-ViT baseline (ablation)RepQ-ViT with uniform quantization · ImageNet W4/A4, ViT-Btop-1 accuracy: 67.61 -> 72.07Improved
add NormQuant alone (ablation)uniform-quantized baseline · ImageNet W4/A4, ViT-Btop-1 accuracy: 67.61 -> 70.83Improved
add DeMax alone (ablation)uniform-quantized baseline · ImageNet W4/A4, ViT-Btop-1 accuracy: 67.61 -> 68.30Improved
add DeMax on top of NormQuant (ablation)UQ-ViT · ImageNet W4/A4, DeiT-Ttop-1 accuracy: 58.65 -> 59.71Improved
apply NormQuant to fc1 (ablation)UQ-ViT · ImageNet W4/A4, DeiT-Stop-1 accuracy: 57.63 -> 72.13 (+6.99% stated for fc1)Improved
apply NormQuant to qkv (ablation)UQ-ViT · ImageNet W4/A4, DeiT-Stop-1 accuracy: 61.02 -> 72.13 (+5.61% stated for qkv)Improved
apply NormQuant to fc2 (ablation)UQ-ViT · ImageNet W4/A4, DeiT-Stop-1 accuracy: 69.92 -> 72.13 (+1.92% stated for fc2)Improved
apply NormQuant to proj (ablation)UQ-ViT · ImageNet W4/A4, DeiT-Stop-1 accuracy: 72.01 -> 72.13 (+0.30% stated for proj)No clear effect
use uniform-only UQ-ViT instead of non-uniform ERQ at 6-bitUQ-ViT · ImageNet W6/A6top-1 accuracy: DeiT-S 79.07 vs ERQ 79.03; Swin-B 84.99 vs ERQ 85.02No clear effect
UQ-ViT (uniform) versus ERQ at 4-bitUQ-ViT · ImageNet W4/A4top-1 accuracy: ViT-B 72.07 vs ERQ 76.63; Swin-S 79.93 vs ERQ 80.74Mixed
apply UQ-ViT to Mask R-CNN Swin-T at 4-bitMask R-CNN Swin-T · COCO W4/A4APbox: 36.8 -> 39.0 (vs ERQ)Improved

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