Unsupervised Anomaly Detection: Encode-Then-Decompose Architectures vs. Autoencoders on Benchmark Datasets

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How do unsupervised anomaly detection models based on encode-then-decompose architectures compare to standard autoencoders in terms of detection accuracy on benchmark datasets with varying. Abstract The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. 7 claims were extracted from source literature; 7 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How do unsupervised anomaly detection models based on encode-then-decompose architectures compare to standard autoencoders in terms of detection accuracy on benchmark datasets with varying contamination ratios?

Autonomous literature synthesis. Automated review score: 7.5/10. Full text and citation available at Assignee Research.