AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shifts

Xi Chen, Maojun Zhang, Yu Liu, Shen Yan

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 2 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 mixture-of-experts (multiple experts instead of one) (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-sensor)mIoU: 63.41 -> 66.19Improved
add mixture-of-experts (multiple experts instead of one) (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-regional)mIoU: 59.37 -> 60.32Improved
add mixture-of-experts (multiple experts instead of one) (ablation)SpectralMoE (DINOv3-Large) · FLAIR (cross-regional)mIoU: 60.82 -> 63.18Improved
use separate gating networks for visual and depth (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-sensor)mIoU: 63.44 -> 66.19Improved
use separate gating networks for visual and depth (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-regional)mIoU: 58.97 -> 60.32Improved
use separate gating networks for visual and depth (ablation)SpectralMoE (DINOv3-Large) · FLAIR (cross-regional)mIoU: 61.95 -> 63.18Improved
add depth features from PromptDA (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-sensor)mIoU: 63.52 -> 66.19Improved
add depth features from PromptDA (ablation)SpectralMoE (DINOv3-Large) · FLAIR (cross-regional)mIoU: 63.07 -> 63.18No clear effect
fuse depth via cross-attention instead of simple addition (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-regional)mIoU: 58.35 -> 60.32Improved
fuse depth via cross-attention instead of simple addition (ablation)SpectralMoE (DINOv3-Large) · Five-Billion-Pixels (cross-sensor)mIoU: 63.48 -> 66.19Improved
increase number of experts beyond 6 (ablation)SpectralMoE · FBP-CS/FBP-CR/FLAIR-CRmIoU: peak at Ne=6Hurt
SpectralMoE adapter instead of REIN/DepthForge/SET on frozen backboneDOFA/DINOv3 · 7 DGSS benchmarksmIoU: e.g. 56.61 -> 59.83 (WHU-OHS)Improved

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