Few-Shot One-Class Classification via Meta-Learning

1 code implementation • 8 Jul 2020 • Ahmed Frikha, Denis Krompaß, Hans-Georg Köpken, Volker Tresp

Our experiments on eight datasets from the image and time-series domains show that our method leads to better results than classical OCC and few-shot classification approaches, and demonstrate the ability to learn unseen tasks from only few normal class samples.

Classification Few-Shot Learning +4