HyperAI

Semi Supervised Semantic Segmentation On 10

Metrics

Validation mIoU

Results

Performance results of various models on this benchmark

Model Name
Validation mIoU
Paper TitleRepository
SemiVL (ViT-B/1687.3SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)80.01Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
PrevMatch (ResNet-101)81.6Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
AllSpark82.12AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)81.8CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
DMT (DeepLab v2, ResNet-50)74.85DMT: Dynamic Mutual Training for Semi-Supervised Learning
UniMatch (ViT-B/16)84.0SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PrevMatch (ResNet-50)79.3Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
UniMatch (DeepLab v3 with ResNet-101)81.2Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
UniMatch V2 (DINOv2-B)90.8UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained)73.7GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
U2PL (DeepLab v3+ with ResNet-101)79.5Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
S4MC81.56Semi-Supervised Semantic Segmentation via Marginal Contextual Information
S4MC (R50)0.7941Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference)78.08Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
0 of 15 row(s) selected.