Classification and Uncertainty Quantification of Corrupted Data using Semi-Supervised Autoencoders. (arXiv:2105.13393v2 [cs.LG] UPDATED)

Parametric and non-parametric classifiers often have to deal with real-world
data, where corruptions like noise, occlusions, and blur are unavoidable -
posing significant challenges. We present a probabilistic approach to classify
strongly corrupted data and quantify uncertainty, despite the model only having
been trained with uncorrupted data. A semi-supervised autoencoder trained on
uncorrupted data is the underlying architecture. We use the decoding part as a
generative model for realistic data and extend it by convolutions, masking, and
additive Gaussian noise …

architecture arxiv autoencoder challenges classification classifiers data deal decoding generative masking noise non-parametric parametric part quantification semi-supervised statistical uncertainty world