AI Paper Atlas

Research map / Architectures and efficiency / Quantization

I&S-ViT: An Inclusive & Stable Method for Post-Training ViTs Quantization

Yunshan Zhong, Jiawei Hu, Mingbao Lin, Mengzhao Chen, Rongrong Ji

TPAMI 2025 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 25 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 shift-uniform-log2 quantizer (SULQ) over log2 quantizer (ablation)DeiT-S PTQ · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 3.36 -> 20.70Improved
add smooth optimization strategy (SOS) (ablation)DeiT-S PTQ · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 3.36 -> 45.19Improved
add SULQ on top of SOS (ablation)DeiT-S PTQ · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 45.19 -> 55.78Improved
add SOS on top of SULQ (ablation)DeiT-S PTQ · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 20.70 -> 55.78Improved
use SULQ instead of log2 quantizer for post-Softmax (ablation)I&S-ViT · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 52.60 -> 55.78Improved
use SULQ instead of uniform quantizer for post-Softmax (ablation)I&S-ViT · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 44.79 -> 55.78Improved
increase calibration images from 32 to 1024 (ablation)I&S-ViT · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 39.70 -> 55.78Improved
increase calibration images from 512 to 1024 (ablation)I&S-ViT · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 54.13 -> 55.78Improved
increase calibration images from 1024 to 2048 (ablation)I&S-ViT · ImageNet W3/A3 (DeiT-S)top-1 accuracy (%): 55.78 -> 55.89No clear effect
use I&S-ViT instead of RepQ-ViT (3-bit ViT-B)ViT-B PTQ · ImageNet W3/A3 (ViT-B)top-1 accuracy (%): 0.14 -> 63.77Improved
use I&S-ViT instead of RepQ-ViT (4-bit ViT-B)ViT-B PTQ · ImageNet W4/A4 (ViT-B)top-1 accuracy (%): 68.48 -> 80.07Improved
use I&S-ViT instead of RepQ-ViT (4-bit Swin-S detection)Mask R-CNN Swin-S · COCO W4/A4AP box: 44.2 -> 43.4Hurt

Later papers that compared with this method

1 later accepted paper reports I&S-ViT 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 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