Anomaly & Out-of-Distribution Detection Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Anomaly and out-of-distribution detection asks when a model should say "I haven't seen this before." The ten papers here span the main families — generative, energy-based, contrastive and reconstructive — and include two concise surveys to orient newcomers.

Anomaly & Out-of-Distribution Detection: 10 key papers

1. Deep Learning for Anomaly Detection: A Review
   Pang et al. arXiv 2020.
2. Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
   Schlegl et al. arXiv 2017.
3. GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
   Akcay et al. arXiv 2018.
4. Deep One-Class Classification
   Ruff et al. International Conference on Machine Learning 2018.
5. Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction
   Sakurada and Yairi. 2014.
6. Efficient GAN-Based Anomaly Detection
   Zenati et al. arXiv 2018.
7. PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
   Defard et al. arXiv 2020.
8. Explainable Deep One-Class Classification
   Liznerski et al. arXiv 2020.
9. Classification-Based Anomaly Detection for General Data
   Bergman and Hoshen. arXiv 2020.
10. Deep Semi-Supervised Anomaly Detection
    Ruff et al. arXiv 2019.

Related reading lists

• Out-of-Distribution & Robustness
• Active Learning & Adaptive Sampling
• Explainable AI & Interpretability
• Contrastive & Self-Supervised Learning
• Score-Based Generative Modeling
• Generative Modeling
• Imitation Learning and Inverse RL
• Robust & Risk-Sensitive RL