HyperAI초신경

Semi Supervised Semantic Segmentation On 27

평가 지표

Validation mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
UniMatch V2 (DINOv2-B)	86.3	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
SemiVL (ViT-B/16)	84.0	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (ViT-B/16)	77.9	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PrevMatch (ResNet-101)	77.0	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)	76.4	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
AllSpark	76.07	AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
UniMatch (DeepLab v3+ with ResNet-101)	75.20	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
S4MC	74.72	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PrevMatch (ResNet-50)	73.4	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
LogicDiag (DeepLab v3+ with ResNet-101)	73.3	Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation
CW-BASS (DeepLab v3+ with ResNet-50)	72.8	CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation
U2PL (DeepLab v3+ with ResNet-101)	68.0	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
CPS (DeepLab v3+ with ResNet-101)	64.1	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
CPCL (DeepLab v3+ with ResNet-50)	61.88	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

0 of 14 row(s) selected.