방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자가 지도 오토인코더 이상 탐지× | 준지도 오토인코더 이상 탐지× | |
|---|---|---|
| 분야 | 머신러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도 | 2018–2020 | 2018–2020 |
| 창시자≠ | Golan & El-Yaniv; broader self-supervised anomaly detection community | Ruff, L. et al.; Zong, B. et al. |
| 유형≠ | Unsupervised / self-supervised deep learning | Semi-supervised deep anomaly detection |
| 원전≠ | Golan, I. & El-Yaniv, R. (2018). Deep one-class classification via geometric transformations. Advances in Neural Information Processing Systems (NeurIPS), 31. link ↗ | Ruff, L., Vandermeulen, R. A., Franks, B. J., Müller, K.-R., & Kloft, M. (2020). Deep Semi-Supervised Anomaly Detection. In International Conference on Learning Representations (ICLR 2020). link ↗ |
| 별칭 | SSL Autoencoder anomaly detection, self-supervised reconstruction anomaly detection, pretext-task autoencoder anomaly detection, contrastive autoencoder anomaly detection | Semi-supervised AE anomaly detection, SSAD autoencoder, semi-supervised reconstruction-error detection, partially labeled autoencoder anomaly detection |
| 관련≠ | 6 | 5 |
| 요약≠ | Self-supervised autoencoder anomaly detection trains an autoencoder using self-supervised pretext tasks — such as predicting geometric transformations or solving jigsaw puzzles — on unlabeled normal data, then flags as anomalous any input whose reconstruction error or pretext-task score deviates substantially from the learned normal distribution. | Semi-supervised Autoencoder Anomaly Detection trains a neural autoencoder primarily on normal (unlabeled) data, then uses a small set of labeled anomalies to refine decision boundaries, detecting anomalies as samples with high reconstruction error. It bridges the gap between purely unsupervised autoencoders and fully supervised classifiers when labels are scarce but some known anomalies exist. |
| ScholarGate데이터셋 ↗ |
|
|