HyperAI超神経

プラットフォーム

Single Object Discovery On Coco 20K

評価指標

CorLoc

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
IMST	72.2	K-means for unsupervised instance segmentation using a self-supervised transformer
MOVE + CAD	71.9	MOVE: Unsupervised Movable Object Segmentation and Detection
MOVE	66.6	MOVE: Unsupervised Movable Object Segmentation and Detection
TokenCut + CAD	62.6	Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
TokenCut	58.8	Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
LOST + CAD	57.5	Localizing Objects with Self-Supervised Transformers and no Labels
rOSD + CAD	53.0	Toward unsupervised, multi-object discovery in large-scale image collections
LOST	50.7	Localizing Objects with Self-Supervised Transformers and no Labels
rOSD	48.5	Toward unsupervised, multi-object discovery in large-scale image collections
DDT+	38.2	Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming

0 of 10 row(s) selected.

Single Object Discovery On Coco 20K | SOTA | HyperAI超神経