Adaptive Deviation Learning combines a soft-label deviation loss with instance reweighting to improve visual anomaly detection when the training set contains unlabeled anomalies.
Anomaly detection via reverse distillation from one-class embedding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination
Adaptive Deviation Learning combines a soft-label deviation loss with instance reweighting to improve visual anomaly detection when the training set contains unlabeled anomalies.