Machine learningMachine learning

自监督 K-均值

自监督 K-均值是一种聚类技术，它将 K-均值分配与自监督表示学习相结合。该模型在将无标签数据点聚类到 K 个组之间进行交替，并使用这些聚类分配作为伪标签来改进底层特征表示，从而在没有任何人工标注的真实标签的情况下产生越来越连贯的聚类。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

The neighbourhood of related methods — select a node to explore.

自监督 K-均值

Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep Clustering for Unsupervised Learning of Visual Features. In Proceedings of the European Conference on Computer Vision (ECCV), 132–149. link ↗
Self-supervised learning. Wikipedia. link ↗

ScholarGate. (2026, June 3). Self-supervised K-means Clustering. ScholarGate. https://scholargate.app/zh/machine-learning/self-supervised-k-means

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.