HyperAI超神经

Unsupervised Image Classification On Stl 10

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
TURTLE (CLIP + DINOv2)	99.7	Let Go of Your Labels with Unsupervised Transfer
HUME	90.8	-
MV-MR	89.67	MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
RUC	86.7	Improving Unsupervised Image Clustering With Robust Learning
ScatSimCLR	85.11	ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets
SCAN	80.90	SCAN: Learning to Classify Images without Labels
TSUC	66.50	Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification
IIC	61.00	Invariant Information Clustering for Unsupervised Image Classification and Segmentation
IPCL (ResNet18)	-	IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

0 of 9 row(s) selected.

HyperAI超神经

Unsupervised Image Classification On Stl 10

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
TURTLE (CLIP + DINOv2)	99.7	Let Go of Your Labels with Unsupervised Transfer
HUME	90.8	-
MV-MR	89.67	MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
RUC	86.7	Improving Unsupervised Image Clustering With Robust Learning
ScatSimCLR	85.11	ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets
SCAN	80.90	SCAN: Learning to Classify Images without Labels
TSUC	66.50	Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification
IIC	61.00	Invariant Information Clustering for Unsupervised Image Classification and Segmentation
IPCL (ResNet18)	-	IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

0 of 9 row(s) selected.

Unsupervised Image Classification On Stl 10 | SOTA | HyperAI超神经