TL;DR
A novel large multimodal model applying vision experts for industrial anomaly detection (abbreviated as Myriad), which treats conventional IAD models as VEs and converts their anomaly maps into lightweight prompts that steer a frozen Q-Former toward suspicious regions, while a compact low-rank adapter shapes features for IAD.
Zero-shot industrial anomaly detection (ZIAD) aims to develop a unified model capable of directly identifying unseen anomaly categories in images without requiring reference samples. Recently, large-scale Vision-Language Models (VLMs) such as CLIP have shown great potential for solving this task. However, existing meth...
Extensive experiments conducted on ten real-world industrial anomaly segmentation datasets demonstrate the superior performance of LCPCLIP in detecting anomalies without any prior knowledge of the dataset categories, which sets a new benchmark for adaptability and generalization in industrial applications.
InspectorGPT, a VLM framework centered on comparative reasoning, is proposed, which demonstrates superior multi-dimensional performance and generalization to unseen benchmarks, validating comparative reasoning for comprehensive industrial inspection.
The HCG-MLLMAD - Hierarchical Cross-Modal Grounding framework of Multimodal Large Language Model-based Anomaly Detection - a variant of the original Light-MLLMAD architecture with multi-scale visual feature pyramids, prompt routing, and a hierarchical cross-attention fusion mechanism is presented.
This paper introduces the first deployment-aware benchmarking protocol for IAD, bridging the gap between academic performance and practical industrial requirements, and highlights the limitations of current benchmark practices.
SPARC is presented, a few-shot calibration method that intercepts patch features between encoder and detector and removes a closed-form, spatially indexed estimate of deployment-time nuisance through per-cell subspace projection and uses the algebraic saturation rank on the encoder's native patch grid.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
