Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

4 code implementations • 28 May 2020 • Oliver Rippel, Patrick Mertens, Dorit Merhof

We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large natural image datasets are well suited to describe normality and detect even subtle anomalies in a transfer learning setting.

Anomaly Detection Transfer Learning