Semi Supervised Semantic Segmentation On 10

Metrics

Validation mIoU

Results

Performance results of various models on this benchmark

		Paper Title
UniMatch V2 (DINOv2-B)	90.8	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
SemiVL (ViT-B/16	87.3	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (ViT-B/16)	84.0	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
AllSpark	82.12	AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)	81.8	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
PrevMatch (ResNet-101)	81.6	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
S4MC	81.56	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
UniMatch (DeepLab v3 with ResNet-101)	81.2	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)	80.01	Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
U2PL (DeepLab v3+ with ResNet-101)	79.5	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
PrevMatch (ResNet-50)	79.3	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference)	78.08	Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
DMT (DeepLab v2, ResNet-50)	74.85	DMT: Dynamic Mutual Training for Semi-Supervised Learning
GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained)	73.7	GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
S4MC (R50)	0.7941	Semi-Supervised Semantic Segmentation via Marginal Contextual Information

0 of 15 row(s) selected.