similarity (SSIM) loss can detect morphological novelties that are not detected by PCA, GANs, and mean squared error autoencoders, but that the latter methods are better suited for detecting spectral novelties—i.e., the best method for a given setting depends on the type of novelties that a...
tribution. CompCaorminpgariFnigg uFirgeusr7e 7a nandd9 F, iigtucrea n9, bite cdanis bcoe vdeisrceodvetrheadt twhaitt hwitthhe thaep appepaeraarnacneceo offt thhee ttaarrggeett,, the dunetdeecrttttohian eukg dnincedtageeprctttahaibk...