方法对比

	自监督自编码器异常检测	变分自编码器
领域	机器学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2018–2020	2014
提出者	Golan & El-Yaniv; broader self-supervised anomaly detection community	Kingma, D. P. & Welling, M.
类型	Unsupervised / self-supervised deep learning	Deep generative latent-variable model (encoder–decoder)
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.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
别名	SSL Autoencoder anomaly detection, self-supervised reconstruction anomaly detection, pretext-task autoencoder anomaly detection, contrastive autoencoder anomaly detection	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
相关	6	5
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.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.