Semi Supervised Semantic Segmentation On 29

Metriken

Validation mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
UniMatch V2 (DINOv2-B)	88.9	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
SemiVL (ViT-B/16)	86.0	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (ViT-B/16)	82.0	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
AllSpark	79.77	AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
PrevMatch (ResNet-101)	79.6	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)	79.4	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
S4MC	79.09	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
UniMatch (DeepLab v3+ with ResNet-101)	78.80	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
LogicDiag (DeepLab v3+ with ResNet-101)	77.9	Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation
PrevMatch (ResNet-50)	77.5	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
U2PL (DeepLab v3+ with ResNet-101)	73.7	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
CPCL (DeepLab v3+ with ResNet-50)	72.14	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
CPS (DeepLab v3+ with ResNet-101)	71.7	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

0 of 13 row(s) selected.