AI Paper Atlas

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

Triad: Empowering LMM-based Anomaly Detection with Expert-guided Region-of-Interest Tokenizer and Manufacturing Process

Yuanze Li, Shihao Yuan, Haolin Wang, Qizhang Li, Ming Liu, Chen Xu, Guangming Shi, Wangmeng Zuo

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 15 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 manufacturing process text to general-purpose LMMsGPT-4o, Qwen2-VL, LLaVA-OneVision · MVTec-AD 0-shotaccuracy: GPT-4o 82.2% -> 67.9%; Qwen2-VL 7B 84.4% -> 61.1%Hurt
add manufacturing process text to TriadTriad-ov 7B · MVTec-AD 0-shotaccuracy: 91.2% -> 92.6%Improved
train LLaVA-1.6-7B with Triad (InstructIAD, CoT-M, EG-RoI)LLaVA-1.6-7B · MVTec-AD 0-shotaccuracy: 76.9% -> 85.0%Improved
add InstructIAD fine-tuning (ablation)LLaVA-1.6-mistral-7B · MVTec-AD 0-shotaccuracy: 76.9% -> 78.8%Improved
add CoT-M data organization (ablation)Triad with EG-RoI · MVTec-AD 0-shot + MFG processaccuracy: 83.9% -> 87.5%Improved
add CoT-M data organization (ablation)Triad with EG-RoI · MVTec-AD 0-shot (no MFG)accuracy: 85.4% -> 85.0%No clear effect
add EG-RoI tokenizer (ablation)Triad (InstructIAD + CoT-M) · MVTec-AD 0-shotaccuracy: 79.8% -> 85.0%Improved
replace AnyRes with EG-RoI (ablation)LLaVA-1.6-mistral-7B fine-tuned · MVTec-AD small/medium/large defectsdefect detection rate: small 90.9% -> 95.5%; large 65.7% -> 81.8%; normal 82.9% -> 72.8%Mixed
use a higher-quality vision expert (MuSc vs April-GAN) (ablation)EG-RoI · MVTec-AD 0-shotaccuracy: 83.0% -> 85.0% (base); P-AUROC 87.6% -> 97.3%Improved
supply random boxes instead of expert regions (ablation)EG-RoI · MVTec-AD 0-shot + MFGaccuracy: 87.5% -> 83.4%Hurt
vary source of manufacturing process (Web, LLM, GPT) (ablation)Triad-ov 7B · MVTec-AD 0-shotaccuracy: 91.2% -> 91.8% (Web), 92.6% (LLM), 92.2% (GPT)Improved
provide one normal reference image (1-shot)general-purpose LMMs · MVTec-ADaccuracy: GPT-4o 82.2% -> 77.6%; Qwen2-VL 72B 87.1% -> 92.0%Mixed

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