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 FeaturesPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Self-Supervised Learning | 4 | 19.05% |
Clustering | 4 | 19.05% |
Graph Learning | 2 | 9.52% |
Change Detection | 1 | 4.76% |
Image Classification | 1 | 4.76% |
Anomaly Detection | 1 | 4.76% |
Speech Recognition | 1 | 4.76% |
Face Clustering | 1 | 4.76% |
imbalanced classification | 1 | 4.76% |