Semi Supervised Semantic Segmentation On 42

Validation mIoU

Results

Performance results of various models on this benchmark

		Paper Title
UniMatch V2	46.7	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
SemiVL	37.2	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
AEL	33.2	Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
UniMatch	31.5	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
CutMix	29.8	Semi-supervised semantic segmentation needs strong, varied perturbations

0 of 5 row(s) selected.