AI Paper Atlas

Research map / Detection and segmentation / CNN features

Low-Resolution Self-Attention for Semantic Segmentation

Yu-Huan Wu, Shichen Zhang, Yun Liu, Le Zhang, Xin Zhan, Daquan Zhou, Jiashi Feng, Ming‐Ming Cheng, Liangli Zhen

TPAMI 2025 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 39 citations (OpenAlex)

Read the paper

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
increase fixed pooled size of LRSA from 4x4 to 16x16 (ablation)LRFormer-S · ADE20K valmIoU: 46.3% -> 48.5%Improved
increase pooled size beyond 16x16 (32x32, 48x48, 64x64) (ablation)LRFormer-S · ADE20K valmIoU: 48.5% -> 48.6%, 48.7%, 48.5% with FLOPs 40G -> 52G, 74G, 108GNo clear effect
add depth-wise convolution before LRSA (ablation)LRFormer-S · ADE20K valmIoU: 48.0% -> 48.5%Improved
add depth-wise convolution in the FFN (ablation)LRFormer-S · ADE20K valmIoU: 47.1% -> 48.5%Improved
add both depth-wise convolutions (ablation)LRFormer-S · ADE20K valmIoU: 44.7% -> 48.5%Improved
add both depth-wise convolutions (ablation)LRFormer-S · ImageNet-1K (100 epochs)top-1 accuracy: 80.4% -> 81.6%Improved
use 16x16 pooled size instead of 4x4 on small objects (ablation)LRFormer-S · ADE20K small-object classesmIoU: 33.7% -> 36.2%Improved
use LRSA decoder instead of OCR head (ablation)LRFormer-S · ADE20K valmIoU: 48.0% -> 49.5%Improved
use LRSA decoder instead of PPM, DA or CC heads (ablation)LRFormer-S · ADE20K valmIoU: 48.4% -> 49.5% (PPM), 48.9% -> 49.5% (DA), 48.6% -> 49.5% (CC)Improved
replace SegFormer-B2 decoder with LRSA decoder (ablation)SegFormer-B2 · ADE20K valmIoU: 46.5% -> 47.3%Improved
increase decoder dimension from 128 to 384 (ablation)LRFormer-S · ADE20K valmIoU: 47.8% -> 49.5%Improved
increase decoder dimension beyond 384 (512, 768, 1024) (ablation)LRFormer-S · ADE20K valmIoU: 49.5% -> 49.6%, 49.2%, 49.2%No clear effect

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