Research map / Label-efficient and robust learning / OOD and anomaly detection
Perturbation Learning Based Anomaly Detection
Jinyu Cai, Jicong Fan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn small perturbations to create pseudo-anomalies and train a normal-vs-perturbed classifier, vs DSVDD | DSVDD · CIFAR-10 one-class | AUC (%): 64.8 -> 75.1 | Improved |
| same, vs best prior (IGD Scratch) | IGD (Scratch) · CIFAR-10 one-class | AUC (%): 74.3 -> 75.1 | Improved |
| same, vs HRN | HRN · Fashion-MNIST one-class | AUC (%): 92.8 -> 93.5 | Improved |
| same, vs GOCC on small tabular data | GOCC · Thyroid | F1-score (%): 76.8 -> 76.6 | No clear effect |
| same, vs GOCC on small tabular data | GOCC · Arrhythmia | F1-score (%): 61.8 -> 71.0 | Improved |
| same, vs DSVDD with multi-class normal data | DSVDD · CIFAR-10 multi-class normal | AUC (%): 63.6 -> 72.7 | Improved |
| same, vs DSVDD with multi-class normal data | DSVDD · Fashion-MNIST multi-class normal | AUC (%): 70.9 -> 75.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DROCC* — DROCC: Deep Robust One-Class Classification (ICML 2020) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Deep One-Class Classification (ICML 2018 · similarity 0.85)
- Deep Semi-Supervised Anomaly Detection (ICLR 2020 · similarity 0.85)
- Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data (ICML 2024 · similarity 0.84)
- ResAD: A Simple Framework for Class Generalizable Anomaly Detection (NeurIPS 2024 · similarity 0.83)
- Unsupervised Anomaly Detection for Tabular Data Using Deep Noise Evaluation (AAAI 2025 · similarity 0.83)
- Normal-Abnormal Guided Generalist Anomaly Detection (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
