Research map / Label-efficient and robust learning / OOD and anomaly detection
Deep One-Class Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| one-class objective instead of soft-boundary | Deep SVDD · MNIST and CIFAR-10 | AUC | Helped |
| one-class vs soft-boundary on GTSRB | Deep SVDD · GTSRB stop signs adversarial | AUC: 77.8 -> 80.3 | Helped |
| Deep SVDD vs DCAE on GTSRB | Deep SVDD · GTSRB stop signs adversarial | AUC: 79.1 -> 80.3 | Helped |
| Deep SVDD vs KDE on CIFAR-10 truck | Deep SVDD · CIFAR-10 truck | AUC: 76.0 -> 73.1 | Hurt |
| Deep SVDD vs KDE on CIFAR-10 frog | Deep SVDD · CIFAR-10 frog | AUC: 74.9 -> 67.7 | Hurt |
| Deep SVDD vs OC-SVM on MNIST digit 2 | Deep SVDD · MNIST digit 2 | AUC: 82.5 -> 91.7 | Helped |
| Deep SVDD vs shallow baselines on MNIST | Deep SVDD · MNIST | AUC | Helped |
| AnoGAN on small training set | AnoGAN · GTSRB stop signs | AUC | Hurt |
| deep methods vs shallow methods on adversarial detection | deep methods · GTSRB stop signs | AUC | Helped |
Closest papers by meaning
- Adversarially Learned One-Class Classifier for Novelty Detection (CVPR 2018 · similarity 0.88)
- ResAD: A Simple Framework for Class Generalizable Anomaly Detection (NeurIPS 2024 · similarity 0.86)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.85)
- ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining (NeurIPS 2025 · similarity 0.85)
- We Need to Rethink Benchmarking in Anomaly Detection (NeurIPS 2026 · similarity 0.84)
- Dense Projection for Anomaly Detection (AAAI 2024 · similarity 0.84)
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.