Browse › Computer Vision › Multi-class Anomaly Detection › VisA
VisA Benchmark (Multi-class Anomaly Detection)
Multi-class Anomaly Detection is a task that identifies anomalies by jointly learning and detecting outliers across multiple classes, in contrast to traditional Anomaly Detection, which typically focuses on identifying anomalies within a single class.
The archive carries no text for this table; the description above is the archive's text for the task Multi-class Anomaly Detection. archive 2025-07-28
Results archive 2025-07-28
No rows in the archive for this table at snapshot 2025-07-28. It declares 1 metric (Detection AUROC) but no result was ever recorded against it. That says nothing about whether results exist elsewhere.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections