HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Image Clustering On Imagenet 10

评估指标

Accuracy

NMI

评测结果

各个模型在此基准测试上的表现结果

模型名称	Accuracy	NMI	Paper Title	Repository
JULE	0.300	0.175	Joint Unsupervised Learning of Deep Representations and Image Clusters
ConCURL	0.958	0.907	Representation Learning for Clustering via Building Consensus
DPAC	0.97	0.925	Deep Online Probability Aggregation Clustering	-
CoHiClust	0.953	0.907	Contrastive Hierarchical Clustering
VAE	0.334	0.193	Auto-Encoding Variational Bayes
SPICE (Full ImageNet pre-train)	0.969	0.927	SPICE: Semantic Pseudo-labeling for Image Clustering
TCL	0.895	0.875	Twin Contrastive Learning for Online Clustering
IDFD	0.954	0.898	Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
MMDC	0.811	0.719	Multi-Modal Deep Clustering: Unsupervised Partitioning of Images
TAC	0.992	0.985	Image Clustering with External Guidance
ProPos*	0.962	0.908	Learning Representation for Clustering via Prototype Scattering and Positive Sampling
CC	0.893	0.859	Contrastive Clustering
DEC	0.381	0.282	Unsupervised Deep Embedding for Clustering Analysis
C3	0.942	0.905	C3: Cross-instance guided Contrastive Clustering
DCCM	0.71	0.608	Deep Comprehensive Correlation Mining for Image Clustering
DAC	0.527	0.394	Deep Adaptive Image Clustering
GAN	0.346	0.225	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
ProPos	0.956	0.896	Learning Representation for Clustering via Prototype Scattering and Positive Sampling

0 of 18 row(s) selected.