Research map / Label-efficient and robust learning / OOD and anomaly detection
Learning Competitive and Discriminative Reconstructions for Anomaly Detection
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 |
|---|---|---|---|
| Use CoRA's competitive two-decoder reconstruction and transductive label assignment instead of DAOC | Anomaly detection · ImageNet-20 | F1: 0.945 -> 0.960 | Helped |
| Use CoRA's competitive two-decoder reconstruction and transductive label assignment instead of DRAE | Anomaly detection · Caltech-101 | F1: 0.968 -> 0.954 | Hurt |
| Use CoRA's competitive two-decoder reconstruction and transductive label assignment instead of DAOC | Anomaly detection · Caltech-101 | AUC: 0.944 -> 0.985 | Helped |
| Use CoRA's competitive two-decoder reconstruction and transductive label assignment instead of DAOC | Anomaly detection · CIFAR-10 | F1: 0.876 -> 0.910 | Helped |
| Use CoRA's competitive two-decoder reconstruction and transductive label assignment instead of DAOC | Anomaly detection · CIFAR-10 | AUC: 0.869 -> 0.897 | Helped |
| Use CoRA instead of the strongest listed baseline | Anomaly detection · Caltech-256, 1 inlier category | AUC: 0.948 -> 0.968 | Helped |
| Use CoRA instead of SSGAN | Anomaly detection · Caltech-256, 1 inlier category | F1: 0.977 -> 0.967 | Hurt |
| Use CoRA instead of DAOC | Anomaly detection · Caltech-256, 3 inlier categories | AUC: 0.938 -> 0.962 | Helped |
| Increase the number of outliers in the unlabeled set and use CoRA | CoRA · MNIST | F1 | Helped |
| Use CoRA when the outlier ratio is small | CoRA · MNIST and Fashion-MNIST | F1 | Hurt |
Closest papers by meaning
- How Does Unlabeled Data Provably Help Out-of-Distribution Detection? (ICLR 2024 · similarity 0.87)
- Quantile-Based Maximum Likelihood Training for Outlier Detection (AAAI 2024 · similarity 0.86)
- Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.86)
- Long-Tailed Anomaly Detection with Learnable Class Names (CVPR 2024 · similarity 0.85)
- A Comprehensive Augmentation Framework for Anomaly Detection (AAAI 2024 · similarity 0.85)
- ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effect (AAAI 2025 · similarity 0.85)
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.