AI Paper Atlas

Research map / Detection and segmentation / CNN features

WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation

Zishan Shu, Juntong Wu, Wei Yan, Xudong Liu, Hongyu Zhang, Chang Liu, Youdong Mao, Jie Chen

AAAI 2026 · Detection and segmentation › CNN features · approach: Convolution-transformer backbones · 12 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
use wave propagation (WaveFormer-T) instead of heat conduction (vHeat-T)WaveFormer-T · ImageNet-1K valtop-1 accuracy: 82.2 -> 82.5Improved
use WaveFormer-B instead of Swin-BWaveFormer-B · ImageNet-1K valtop-1 accuracy: 83.5 -> 84.2Improved
use WaveFormer-T instead of vHeat-TWaveFormer-T · COCO box AP (1x)box AP: 45.1 -> 45.8Improved
use WaveFormer-T instead of vHeat-T, throughputWaveFormer-T · COCO Mask R-CNN (1x)FPS: 32.7 -> 32.1 FPSHurt
use WaveFormer-B instead of vHeat-BWaveFormer-B · ADE20K (UperNet)mIoU: 49.6 -> 50.5Improved
use WaveFormer-T instead of vHeat-TWaveFormer-T · COCO box AP (3x)box AP: 47.2 -> 47.4Improved
use WaveFormer-S instead of vHeat-SWaveFormer-S · ImageNet-1K valtop-1 accuracy: 83.6 -> 83.9Improved
use moderate damping and velocity (v=1, alpha=0.1) instead of extreme values (ablation)WaveFormer-B · ADE20K (UperNet)mIoUImproved

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