Shortcut Detection with Variational Autoencoders
For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data. The identification of such spurious correlations, also known as shortcuts, is a challenging problem and has so far been scarcely addressed. In this work, we present a novel approach to detect shortcuts in image and audio datasets by leveraging variational autoencoders (VAEs). The disentanglement of features in the latent space of VAEs allows us to discover feature-target correlations in datasets and semi-automatically evaluate them for ML shortcuts. We demonstrate the applicability of our method on several real-world datasets and identify shortcuts that have not been discovered before.
Code (1)
Tasks
DisentanglementSimilar Papers 제목 키워드 기반
Anomaly Detection With Conditional Variational Autoencoders
Exploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question. Previous works argued tha…
Anomaly DetectionA comparison of classical and variational autoencoders for anomaly detection
This paper analyzes and compares a classical and a variational autoencoder in the context of anomaly detection. To better understand their architecture and functioning, describe their properties and compare their perform…
Anomaly DetectionAn Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction
Video Anomaly Detection (VAD) represents a challenging and prominent research task within computer vision. In recent years, Pose-based Video Anomaly Detection (PAD) has drawn considerable attention from the research comm…
Anomaly DetectionTrajectory PredictionVideo Anomaly DetectionChallenges for Unsupervised Anomaly Detection in Particle Physics
Anomaly detection relies on designing a score to determine whether a particular event is uncharacteristic of a given background distribution. One way to define a score is to use autoencoders, which rely on the ability to…
Anomaly DetectionUnsupervised Anomaly DetectionIncluding Sparse Production Knowledge into Variational Autoencoders to Increase Anomaly Detection Reliability
Digitalization leads to data transparency for production systems that we can benefit from with data-driven analysis methods like neural networks. For example, automated anomaly detection enables saving resources and opti…
Anomaly DetectionTime SeriesTime Series Analysis