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

by   Philipp Joppich, et al.

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.



There are no comments yet.


page 2

page 12

page 13


Probabilistic Autoencoder using Fisher Information

Neural Networks play a growing role in many science disciplines, includi...

Semi-supervised deep learning for high-dimensional uncertainty quantification

Conventional uncertainty quantification methods usually lacks the capabi...

Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords

This paper describes a statistically-principled semi-supervised method o...

Rate-Distortion Optimization Guided Autoencoder for Generative Approach with quantitatively measurable latent space

In the generative model approach of machine learning, it is essential to...

Self-Supervised Hybrid Inference in State-Space Models

We perform approximate inference in state-space models that allow for no...

A Forest from the Trees: Generation through Neighborhoods

In this work, we propose to learn a generative model using both learned ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.