Semi Supervised Video Object Segmentation On 18

Metrics

F-Measure (Seen)

F-Measure (Unseen)

FPS

Jaccard (Seen)

Jaccard (Unseen)

Overall

Results

Performance results of various models on this benchmark

Model Name	F-Measure (Seen)	F-Measure (Unseen)	FPS	Jaccard (Seen)	Jaccard (Unseen)	Overall	Paper Title	Repository
DeAOT-B	88.3	87.5	30.4	83.5	79.1	84.6	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
SwinB-AOTv2-L (all frames, MS)	90.3	89.1	-	85.5	81.0	86.5	Scalable Video Object Segmentation with Identification Mechanism
R50-AOST (L'=3)	88.7	87.7	-	83.8	79.3	84.9	Scalable Video Object Segmentation with Identification Mechanism
DeAOT-L	88.8	87.2	24.7	83.8	79.0	84.7	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Lightweight TrickVOS (PT)	83.3	84	-	79.5	-	-	TrickVOS: A Bag of Tricks for Video Object Segmentation	-
STCN	87.0	87.7	-	82.6	79.4	84.2	Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
STCN (MS)	87.8	88.8	-	83.5	80.8	85.2	Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
DEVA	89.9	89.1	25.3	85.4	89.9	86.2	Tracking Anything in High Quality
R50-DeAOT-L	89.4	88.9	22.4	84.6	80.8	85.9	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
SwinB-DeAOT-L	90.2	88.6	11.9	85.3	80.4	86.1	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
XMem (BL30K, MS)	89.8	89.9	-	85.5	81.8	86.8	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
R50-AOST (L'=2)	88.0	87.1	-	83.3	78.9	84.3	Scalable Video Object Segmentation with Identification Mechanism
R50-AOST (L'=1)	85.6	83.8	-	81.0	754.8	81.5	Scalable Video Object Segmentation with Identification Mechanism
XMem (MS)	89.2	89.8	-	84.9	81.8	86.4	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
RPCMVOS	86.9	87.1	-	82.6	79.1	83.9	Reliable Propagation-Correction Modulation for Video Object Segmentation
SwinB-AOTv2-L (all frames)	88.9	88.0	-	84.2	79.8	85.2	Scalable Video Object Segmentation with Identification Mechanism
STCN + TrickVOS (PT)	86.4	85.5	-	82.1	77.2	-	TrickVOS: A Bag of Tricks for Video Object Segmentation	-
DeAOT-S	87.5	86.8	38.7	82.8	78.1	83.8	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
XMem	88.0	87.1	-	83.6	78.5	84.3	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
DeAOT-T	85.6	84.7	53.4	81.2	76.4	82.0	Decoupling Features in Hierarchical Propagation for Video Object Segmentation

0 of 22 row(s) selected.