mlsanityData to 7 Oct 2026

Deep Transductive Outlier Detection

arXiv 2404.03495 ↗First posted 4 Apr 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Outlier detection (OD) is one of the core challenges in machine learning. Transductive learning, which leverages test data during training, has shown promise in related machine learning tasks, yet remains largely unexplored for modern OD. We present Doust, the first end-to-end transductive deep learning algorithm for outlier detection, which explicitly leverages unlabeled test data to boost accuracy. On the comprehensive ADBench benchmark, Doust achieves an average ROC-AUC of 89%, outperforming all 21 competitors by roughly 10%. Our analysis identifies both the potential and a limitation of transductive OD: while performance gains can be substantial in favorable conditions, very low contamination rates can hinder improvements unless the dataset is sufficiently large.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 57 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

18 of 57 references.

References · 18

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2015Variational Inference with Normalizing Flowscited by 2,161
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  5. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  6. 2020Classification-Based Anomaly Detection for General Datacited by 210
  7. 2022Test-Time Training with Masked Autoencoderscited by 208
  8. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  9. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  10. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  11. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  12. 2023On Diffusion Modeling for Anomaly Detectioncited by 71
6 more
  1. 2023Meta-survey on outlier and anomaly detectioncited by 12
  2. 2019Unsupervised Boosting-based Autoencoder Ensembles for Outlier Detectioncited by 8
  3. 2023UADB: Unsupervised Anomaly Detection Boostercited by 7
  4. 2023Self-Tuning Self-Supervised Image Anomaly Detectioncited by 4
  5. 2022Fault Prognosis in Particle Accelerator Power Electronics Using Ensemble Learningcited by 2
  6. 2023Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunitiescited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Rare anomalies require large datasets: About proving the existence of anomaliescited by 0