Friday, May 2025
02:10 PM - 02:30 PM
Room: LL21CD
Session: Artificial Intelligence for Display Manufacturing I
Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection
Late-News
Description:
Reconstruction-based anomaly detection via denoising diffusion model has limitations in determining appropriate noise parameters that can degrade anomalies while preserving normal characteristics. Also, normal regions can fluctuate considerably during reconstruction, resulting in false detection. In this paper, we propose a method to detect anomalies by analysis of reconstruction trend depending on the degree of degradation, effectively solving the both problems that impede practical application in display inspection.