HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Single Object Discovery On Coco 20K

Metrics

CorLoc

Results

Performance results of various models on this benchmark

Model Name
CorLoc
Paper TitleRepository
MOVE + CAD71.9MOVE: Unsupervised Movable Object Segmentation and Detection
LOST50.7Localizing Objects with Self-Supervised Transformers and no Labels
IMST72.2K-means for unsupervised instance segmentation using a self-supervised transformer-
MOVE66.6MOVE: Unsupervised Movable Object Segmentation and Detection
TokenCut + CAD62.6Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
DDT+38.2Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming-
LOST + CAD57.5Localizing Objects with Self-Supervised Transformers and no Labels
rOSD48.5Toward unsupervised, multi-object discovery in large-scale image collections
rOSD + CAD53.0Toward unsupervised, multi-object discovery in large-scale image collections
TokenCut58.8Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
0 of 10 row(s) selected.