Method evidence record
Self-supervised Autoencoder Anomaly Detection
Self-supervised autoencoder anomaly detection trains an autoencoder using self-supervised pretext tasks — such as predicting geometric transformations or solving jigsaw puzzles — on unlabeled normal data, then flags as anomalous any input whose reconstruction error or pretext-task score deviates substantially from the learned normal distribution.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Self-supervised Autoencoder Anomaly Detection (Pretext-Task Reconstruction-Based Anomaly Detection)
Taxonomic method record · ml-model / machine-learning
- Golan, I. & El-Yaniv, R. (2018). Deep one-class classification via geometric transformations. Advances in Neural Information Processing Systems (NeurIPS), 31. · URL
- Ruff, L., Kauffmann, J. R., Vandermeulen, R. A., Montavon, G., Samek, W., Kloft, M., Dietterich, T. G., & Müller, K.-R. (2021). A unifying review of deep and shallow anomaly detection. Proceedings of the IEEE, 109(5), 756–795. · DOI 10.1109/JPROC.2021.3052449
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.