Trustworthy and resilient AI: a case study in remote ship inspection
Xiaoliang Gong, Heke Zhang, Sunniva Elisabeth Daae Steiro
Deploying AI in real-world environments often leads to performance degradation due to data drift, concept shift, and unforeseen anomalies. This paper presents a scalable approach to building trustworthy and resilient AI for remote ship inspection. Using a defect segmentation AI system as …
no (code pays fourni par la source)