Unsupervised Object Segmentation On

ARI-FG

Results

Performance results of various models on this benchmark

Model Name	ARI-FG	Paper Title
MONET-G	0.70	GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
GENESIS-V2	0.81	GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
AST	0.82	Unsupervised Multi-object Segmentation Using Attention and Soft-argmax
SlotAttention	0.76	GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
GENESIS	0.70	GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

0 of 5 row(s) selected.