GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
Open paper
Benchmark
Model
Rank
Results
weakly-supervised-semantic-segmentation-on
GETAM(vit-hybrid)
#24
Mean IoU: 71.7
weakly-supervised-semantic-segmentation-on-1
GETAM(vitb-hybrid)
#21
Mean IoU: 72.3
Rank counts only results with a code link.