AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Advancing Vision Transformer With Enhanced Spatial Priors

Qihang Fan, Huaibo Huang, Mingrui Chen, Hongmin Liu, Ran He

TPAMI 2026 · Architectures and efficiency › Attention and transformers · approach: Hybrid and interpretable ViT designs · 0 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 Euclidean decay matrix (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 82.3 -> 83.0Improved
add Euclidean decay matrix (ablation)EVT-T · KIT: ADE20K Semantic FPNmIoU: 46.6 -> 48.3Improved
use Euclidean instead of Manhattan distance for decay (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 82.7 -> 83.0Improved
use Euclidean distance (lower JS divergence to learned attention) (ablation)EVT-T · ImageNet-1KJS divergence: 0.20 -> 0.12Improved
add local context enhancement (LCE) (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 82.8 -> 83.0Improved
add conditional position encoding (CPE) (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 82.9 -> 83.0No clear effect
add conv stem (ablation)EVT-T · ADE20K Semantic FPNmIoU: 47.1 -> 48.3Improved
swap grouped and dilated attention order (EuSA_g to EuSA_d) (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 83.0 -> 82.5Hurt
replace 2D grouping with 1D grouping (same 49 tokens, with EuSA) (ablation)EVT-S · ImageNet-1Ktop-1 accuracy: 83.8 -> 83.9No clear effect
increase group size with 1D grouping from 49 to 98 tokens (ablation)EVT-S · ImageNet-1Ktop-1 accuracy: 83.9 -> 84.4Improved
1D grouping instead of 2D at 512 resolution (direct inference) (ablation)EVT-T · ImageNet-1Ktop-1 accuracy: 81.1 -> 82.8Improved
use Minkowski p=3 distance instead of Euclidean (ablation)EVT-Swin-T · COCO Mask R-CNNbox AP: 48.6 -> 44.4Hurt

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