Classification and Uncertainty Quantification of Corrupted Data using Semi-Supervised Autoencoders

TL;DR

This paper introduces a probabilistic semi-supervised autoencoder approach that classifies and quantifies uncertainty in heavily corrupted data, enabling robust classification and data restoration.

Contribution

It presents a novel method combining semi-supervised autoencoders with variational inference to classify corrupted data and estimate uncertainty without training on corrupted examples.

Findings

Model uncertainty correlates with classification correctness

Generative model effectively restores uncorrupted data

Approach outperforms traditional classifiers on corrupted data

Abstract

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 to describe imperfections. This constitutes a statistical inference task in terms of the optimal latent space activations of the underlying uncorrupted datum. We solve this problem approximately with Metric Gaussian Variational Inference (MGVI). The supervision of the autoencoder's latent space allows us to classify corrupted data directly under uncertainty with the statistically inferred latent space activations. Furthermore, we demonstrate that the model uncertainty strongly depends on whether the classification is correct or wrong, setting a basis for a statistical "lie detector" of the classification. Independent of that, we show that the generative model can optimally restore the uncorrupted datum by decoding the inferred latent space activations.