Weakly Supervised Semantic Segmentation On 14

Mean IoU

Results

Performance results of various models on this benchmark

		Paper Title
FMA-WSSS	80.4	Foundation Model Assisted Weakly Supervised Semantic Segmentation
WeakTr (DeiT-S, single-stage)	76.5	WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
FBR	75.9	Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
ViT-PCM	71.4	Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

0 of 4 row(s) selected.