方法对比

	自监督自编码器异常检测	自监督学习
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2018–2020	2018–2020
提出者	Golan & El-Yaniv; broader self-supervised anomaly detection community	LeCun, Y. and community (formalized ~2018–2020)
类型	Unsupervised / self-supervised deep learning	Representation learning paradigm
开创性文献	Golan, I. & El-Yaniv, R. (2018). Deep one-class classification via geometric transformations. Advances in Neural Information Processing Systems (NeurIPS), 31.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
别名	SSL Autoencoder anomaly detection, self-supervised reconstruction anomaly detection, pretext-task autoencoder anomaly detection, contrastive autoencoder anomaly detection	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
相关	6	3
摘要	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.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.