Autoencoder Attractors for Uncertainty Estimation
The reliability assessment of a machine learning model's prediction is an important quantity for the deployment in safety critical applications. Not only can it be used to detect novel sceneries, either as out-of-distribution or anomaly sample, but it also helps to determine deficiencies in the...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The reliability assessment of a machine learning model's prediction is an
important quantity for the deployment in safety critical applications. Not only
can it be used to detect novel sceneries, either as out-of-distribution or
anomaly sample, but it also helps to determine deficiencies in the training
data distribution. A lot of promising research directions have either proposed
traditional methods like Gaussian processes or extended deep learning based
approaches, for example, by interpreting them from a Bayesian point of view. In
this work we propose a novel approach for uncertainty estimation based on
autoencoder models: The recursive application of a previously trained
autoencoder model can be interpreted as a dynamical system storing training
examples as attractors. While input images close to known samples will converge
to the same or similar attractor, input samples containing unknown features are
unstable and converge to different training samples by potentially removing or
changing characteristic features. The use of dropout during training and
inference leads to a family of similar dynamical systems, each one being robust
on samples close to the training distribution but unstable on new features.
Either the model reliably removes these features or the resulting instability
can be exploited to detect problematic input samples. We evaluate our approach
on several dataset combinations as well as on an industrial application for
occupant classification in the vehicle interior for which we additionally
release a new synthetic dataset. |
---|---|
DOI: | 10.48550/arxiv.2204.00382 |