GRC-Net: Global Representation Consistency Network for Unsupervised Multimodal Anomaly Detection

Key points

• Automated quality inspection is essential for ensuring product reliability in manufacturing.While image-based methods effectively capture appearance-related defects, these methods are limited in detecting structural and geometric anomalies, motivating multimodal approaches incorporating 3D information.1
• However, existing methods mainly rely on local patch-level representations, which often lead to unstable reconstruction errors even in normal regions.1
• The proposed method captures holistic contextual information through a global token and suppresses reconstruction noise by minimizing discrepancies between original and predicted embeddings.1
• Experiments on MVTec 3D-AD and Eyecandies demonstrate that GRC-Net consistently outperforms existing methods at both image and pixel levels.1

Sources (1)

• [1]GRC-Net: Global Representation Consistency Network for Unsupervised Multimodal Anomaly Detection
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 02:35 AM

  To address this limitation, we propose GRC-Net, which integrates a global-attention MLP to enforce global representation consistency across patch embeddings with a stable reconstruction module to improve reconstruction stability.

  Automated quality inspection is essential for ensuring product reliability in manufacturing.While image-based methods effectively capture appearance-related defects, these methods are limited in detecting structural and geometric anomalies, motivating multimodal approaches incorporating 3D information.

Extractive summary: sentences quoted from the sources.