Description
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
Papers Using This Method
Jigsaw Game: Federated Clustering2024-07-17The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning2023-07-20DC3DCD: unsupervised learning for multiclass 3D point cloud change detection2023-05-09Self-supervised Learning for Clustering of Wireless Spectrum Activity2022-09-22A Deep Dive into Deep Cluster2022-07-24Learnability and Expressiveness in Self-Supervised Learning2021-09-29A Linkage-based Doubly Imbalanced Graph Learning Framework for Face Clustering2021-07-06A critical analysis of self-supervision, or what we can learn from a single image2019-04-30Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels2019-02-28Deep Clustering for Unsupervised Learning of Visual Features2018-07-15