Self-Supervised Learning

DeepCluster

Introduced by Caron et al. in Deep Clustering for Unsupervised Learning of Visual Features

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

Source: Deep Clustering for Unsupervised Learning of Visual Features

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Clustering 5 21.74%
Self-Supervised Learning 4 17.39%
Graph Learning 2 8.70%
Federated Learning 1 4.35%
Change Detection 1 4.35%
Image Classification 1 4.35%
Anomaly Detection 1 4.35%
Speech Recognition 1 4.35%
Face Clustering 1 4.35%

Components


Component Type
k-Means Clustering
Clustering

Categories