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

العربية

Semi Supervised Semantic Segmentation On 30

المقاييس

Validation mIoU

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Validation mIoU	Paper Title	Repository
LogicDiag (DeepLab v3+ with ResNet-101)	79.4	Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation	-
U2PL (DeepLab v3+ with ResNet-101)	76.2	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
CPCL (DeepLab v3+ with ResNet-50)	74.25	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
S4MC	80.12	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PrevMatch (ResNet-50)	78.6	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
UniMatch (ViT-B/16)	83.3	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
CPS (DeepLab v3+ with ResNet-101)	75.9	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
UniMatch V2 (DINOv2-B)	90.0	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
S4MC (R50)	77.83	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PrevMatch (ResNet-101)	80.4	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
AllSpark	80.75	AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)	80.6	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
SemiVL (ViT-B/16)	86.7	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (DeepLab v3+ with ResNet-101)	79.90	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

0 of 14 row(s) selected.