الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Unsupervised Image Classification On Stl 10

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

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

0 of 9 row(s) selected.

Unsupervised Image Classification On Stl 10 | SOTA | HyperAI