Preprint
Aug 2026
Continuity-Driven Representation Learning for Industrial Defect Detection
Industrial defect detection differs from natural-image object detection because inspection images are captured under controlled conditions and contain large normal-dominant regions with repetitive structures. Defects therefore appear as localized disruptions of otherwise predictable patterns, while conventional detecto...
Minjong Kim, Hyun Jun Kim, Jeongrae Kim et al.
· 0 citations