iFAN: Inference-Aware Learning for Plain Mask Transformers
Open paper
Benchmark
Model
Rank
Results
panoptic-segmentation-on-coco-minival
EoMT-iFAN (ViT-G, 1280²) (extra data)
#3
PQ: 59.6
instance-segmentation-on-coco-minival
EoMT-iFAN (ViT-L, 1280²) (extra data)
#22
mask AP: 50.6
Rank counts only results with a code link.