Semi Supervised Video Object Segmentation On 1

평가 지표

F-measure (Mean)

FPS

Ju0026F

Jaccard (Mean)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F-measure (Mean)	FPS	Ju0026F	Jaccard (Mean)	Paper Title	Repository
SwinB-AOST (L'=3)	86.6	12.0	82.7	78.8	Scalable Video Object Segmentation with Identification Mechanism
XMem (BL30K)	84.7	-	81.2	77.6	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
SwinB-AOT-L	85.1	12.1	81.2	77.3	Associating Objects with Transformers for Video Object Segmentation
PReMVOS	75.8	-	71.6	67.5	PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
SwinB-AOTv2-L	87.9	1.3	84.5	81.0	Scalable Video Object Segmentation with Identification Mechanism
OSVOS-S	62.1	-	57.5	52.9	Video Object Segmentation Without Temporal Information	-
QDMN	85.4	-	81.9	78.1	Learning Quality-aware Dynamic Memory for Video Object Segmentation
LSMVOS	71.2	-	67.4	63.7	LSMVOS: Long-Short-Term Similarity Matching for Video Object
XMem (BL30K, MS)	87.0	-	83.7	80.5	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
CFBI+	81.6	-	78.0	74.4	Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
DEVA	86.8	25.3	83.2	79.6	Tracking Anything with Decoupled Video Segmentation
DeAOT-S	79.0	49.2	75.4	71.9	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
MiVOS	80.2	-	76.5	72.7	Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
CapsuleVOS	55.2	-	51.3	47.4	CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
CFBI	78.5	-	74.8	71.1	Collaborative Video Object Segmentation by Foreground-Background Integration
RMNet	78.1	-	75.0	71.9	Efficient Regional Memory Network for Video Object Segmentation
OSMN	-	-	41.3	37.7	Efficient Video Object Segmentation via Network Modulation
AOT-L	82.3	18.7	78.3	74.3	Associating Objects with Transformers for Video Object Segmentation
RPCMVOS	82.6	-	79.2	75.8	Reliable Propagation-Correction Modulation for Video Object Segmentation
XMem (BL30K, 600p)	85.8	-	82.5	79.1	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

0 of 59 row(s) selected.