2 papers
cs.CV2024
Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection
Lei Fan, Junjie Huang, Donglin Di +4
For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource managem…
cs.CV2024
ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection
Yun Liang, Zhiguang Hu, Junjie Huang +3
Current unsupervised anomaly detection approaches perform well on public datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extract…