Manifolds for Unsupervised Visual Anomaly Detection

1 code implementation • 19 Jun 2020 • Louise Naud, Alexander Lavin

Through theoretical and empirical explorations of manifold shapes, we develop a novel hyperspherical Variational Auto-Encoder (VAE) via stereographic projections with a gyroplane layer - a complete equivalent to the Poincar\'e VAE.

Anomaly Detection whole slide images