paper-with-me

DeepCluster

2000년 도입 · 논문 10편에서 사용

DeepCluster is a self-supervision approach for learning image representations. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network

출처: Deep Clustering for Unsupervised Learning of Visual Features

소개 논문: Deep Clustering for Unsupervised Learning of Visual Features

Self-Supervised Learning · General