AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis

Yishen Liu, Hongchang Chen, Pengcheng Zhao, Yunfan Bao, Yuxi Tian, Jieming Zhang, HAO CHEN, Zhi Zheng, Yongchun Liu, Ying Li, Dongpu Cao

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 1 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 Gated Self-Attention Module (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 75.7 -> 85.9Improved
add Spatial-Textual Feature Fusion (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 77.3 -> 85.9Improved
add Disentangled Token Learning (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 81.7 -> 85.9Improved
add mixed normal-anomalous training (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 83.1 -> 85.9Improved
add normal-prior denoising initialization (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 84.7 -> 85.9Improved
add mixed normal-anomalous training (ablation)GroundingAnomaly · MVTec AD generationIS: 1.74 -> 1.99Improved
add Gated Self-Attention Module (ablation)GroundingAnomaly · VisA (U-Net)pixel AP: 58.1 -> 67.2Improved
use all anomaly images (1/3) instead of 1-shot (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 72.3 -> 85.9Improved
use all anomaly images (1/3) instead of 1-shot (ablation)GroundingAnomaly · VisA (U-Net)pixel AP: 44.3 -> 67.2Improved
use N=4, K=4 tokens instead of N=1, K=1 (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 80.5 -> 85.9Improved
use gated self-attention instead of ungated (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 74.1 -> 85.9Improved
add LoRA to self-attention layers (ablation)GroundingAnomaly · MVTec AD (U-Net)pixel AP: 83.3 -> 85.9Improved

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