HyperAI超神経

プラットフォーム

Image Clustering On Mnist Full

評価指標

Accuracy

NMI

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

			Paper Title
SPC	0.992	0.975	Selective Pseudo-label Clustering
ADEC	0.990	0.971	Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift
N2D (UMAP)	0.987	0.964	N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding
DynAE	0.987	0.964	Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction
DDC-DA	0.986	0.961	Deep Density-based Image Clustering
DEN	0.984	0.956	Interpretable Visualizations with Differentiating Embedding Networks
DTI-Clustering	0.979	0.942	Deep Transformation-Invariant Clustering
EnSC	0.969	0.941	Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering
ClusterGAN	0.973	0.940	Balanced Self-Paced Learning for Generative Adversarial Clustering Network
DBC	0.976	0.937	Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
PSSC	0.964	0.921	Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement
VMM	0.967	0.920	The VampPrior Mixture Model
JULE-RC	0.964	0.917	Joint Unsupervised Learning of Deep Representations and Image Clusters
SR-K-means	-	0.913	Deep clustering: On the link between discriminative models and K-means
GDL	0.965	0.913	Graph Degree Linkage: Agglomerative Clustering on a Directed Graph
Tree-SNE	-	0.864	Tree-SNE: Hierarchical Clustering and Visualization Using t-SNE

0 of 16 row(s) selected.

Image Clustering On Mnist Full | SOTA | HyperAI超神経