HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Single Object Discovery On Coco 20K

평가 지표

CorLoc

평가 결과

이 벤치마크에서 각 모델의 성능 결과

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

0 of 10 row(s) selected.