Dual-Student Knowledge Distillation Networks for Unsupervised Anomaly Detection

Due to the data imbalance and the diversity of defects, student-teacher networks (S-T) are favored in unsupervised anomaly detection, which explores the discrepancy in feature representation derived from the knowledge distillation process to recognize anomalies. However, vanilla S-T network is not stable. Employing identical structures to construct the S-T network may weaken the representative discrepancy on anomalies. But using different structures can increase the likelihood of divergent performance on normal data. To address this problem, we propose a novel dual-student …

anomaly anomaly detection construct cs.ai cs.cv data defects detection distillation diversity feature knowledge network networks process representation unsupervised