Image Clustering On Mnist Test
Metrics
Accuracy
NMI
Results
Performance results of various models on this benchmark
Model Name | Accuracy | NMI | Paper Title | Repository |
|---|---|---|---|---|
| DDC | 0.965 | 0.916 | Deep Density-based Image Clustering | |
| PSSC | 0.967 | 0.919 | Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement | |
| DTI-Clustering | 0.978 | 0.947 | Deep Transformation-Invariant Clustering | |
| GDL | - | 0.91 | Graph Degree Linkage: Agglomerative Clustering on a Directed Graph | |
| N2D (UMAP) | 0.948 | 0.882 | N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding | |
| SR-K-means | 0.863 | 0.873 | Deep clustering: On the link between discriminative models and K-means | |
| DDC-DA | 0.97 | 0.927 | Deep Density-based Image Clustering | |
| AGDL | - | 0.844 | Graph Degree Linkage: Agglomerative Clustering on a Directed Graph | |
| OURS-RC | - | 0.915 | Joint Unsupervised Learning of Deep Representations and Image Clusters | |
| AE+SNNL | 0.962 | 0.903 | Improving k-Means Clustering Performance with Disentangled Internal Representations | |
| DynAE | 0.987 | 0.963 | Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction |
0 of 11 row(s) selected.