AI Paper Atlas

Research map / Detection and segmentation / CNN features

Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation

Guangqian Guo, Aixi Ren, Xuehui Yu, Pengxu Wei, Yong Guo, shan gao

ECCV 2026 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 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
replace simple adapter with static frequency adapter (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8172 -> 0.8312Improved
replace spatial MoE with frequency-domain experts (MoFE) (ablation)FreqDirect MiT-B4 · COVID-19IoU: 0.8230 -> 0.8516Improved
add Spatial Commonality Anchor to MoFE (ablation)FreqDirect MiT-B4 · GDDIoU: 0.8605 -> 0.8938Improved
add Spatial Commonality Anchor to MoFE (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8457 -> 0.8542Improved
use dynamic router instead of fixed uniform routing (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8344 -> 0.8542Improved
use 3 experts instead of 2 (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8419 -> 0.8542Improved
use 4 experts instead of 3 (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8542 -> 0.8525No clear effect
insert FreqDirect in all 4 stages instead of stage 4 only (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8109 -> 0.8542Improved
insert in even layers only vs all layers (ablation)FreqDirect MiT-B4 · COD10KS-measure: 0.8542 -> 0.8532; params 5.26M -> 4.18MNo clear effect
joint training instead of separate training (ablation)FreqDirect · PlantCAMO zero-shotS-measure: 0.4198 -> 0.6453Improved
FreqDirect Swin-L vs FOCUS DINOv2-LFreqDirect · COVID-19IoU: 0.6986 -> 0.8646Improved

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