2 papers
cs.CV2025
MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning
Ylli Sadikaj, Hongkuan Zhou, Lavdim Halilaj +3
Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or…
cs.LG2024
ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks
Zhaoliang Chen, Zhihao Wu, Ylli Sadikaj +5
Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the…