AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition

Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng

TPAMI 2022 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 234 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
smaller initial patch size (16 to 14) (ablation)ViP-Small · ImageNet-1k valtop-1 accuracy (%): 79.8 -> 80.5Improved
add fine-level tokens (7x7 patches plus 4 Permutators) (ablation)ViP-Small · ImageNet-1k valtop-1 accuracy (%): 80.5 -> 81.5Improved
encode fine-level tokens (ablation)ViP-Small · ImageNet-1k valthroughput (img/s): 789 img/s -> 719 img/sHurt
scale model from Small/7 to Medium/7 (ablation)ViP · ImageNet-1k valtop-1 accuracy (%): 81.5 -> 82.7Improved
scale model from Medium/7 to Large/7 (ablation)ViP · ImageNet-1k valtop-1 accuracy (%): 82.7 -> 83.2Improved
add Random Augmentation (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 75.3 -> 77.7 (+2.4)Improved
add CutOut (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 77.7 -> 78.0 (+2.7)Improved
add MixUp (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 78.0 -> 80.2 (+4.9)Improved
add CutMix (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 80.2 -> 80.6 (+5.3)Improved
add height information encoding (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 72.8 -> 80.2Improved
add width information encoding (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 72.7 -> 80.2Improved
use Weighted Permute-MLP instead of vanilla Permute-MLP (ablation)ViP-Small/14 · ImageNet-1k valtop-1 accuracy (%): 80.2 -> 80.6Improved

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