Image Clustering On Tiny Imagenet

Metrics

Accuracy

NMI

Results

Performance results of various models on this benchmark

			Paper Title
PRO-DSC	0.698	0.805	Exploring a Principled Framework For Deep Subspace Clustering
ITAE	0.6823	0.8178	Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering
SPICE	0.305	0.449	SPICE: Semantic Pseudo-labeling for Image Clustering
IMC-SwAV (Best)	0.282	0.526	Information Maximization Clustering via Multi-View Self-Labelling
IMC-SwAV (Avg+-)	0.279	0.485	Information Maximization Clustering via Multi-View Self-Labelling
C3	0.141	0.335	C3: Cross-instance guided Contrastive Clustering
CC	0.14	0.34	Contrastive Clustering
MMDC	0.119	0.274	Multi-Modal Deep Clustering: Unsupervised Partitioning of Images
DCCM	0.108	0.224	Deep Comprehensive Correlation Mining for Image Clustering
DAC	0.066	0.190	Deep Adaptive Image Clustering
GAN	0.041	0.135	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
DEC	0.037	0.115	Unsupervised Deep Embedding for Clustering Analysis
VAE	0.036	0.113	Auto-Encoding Variational Bayes
JULE	0.033	0.102	Joint Unsupervised Learning of Deep Representations and Image Clusters

0 of 14 row(s) selected.

Image Clustering On Tiny Imagenet | SOTA | HyperAI