HyperAI초신경

Semi Supervised Video Object Segmentation On 21

평가 지표

F

FPS

J

Ju0026F

평가 결과

이 벤치마크에서 각 모델의 성능 결과

					Paper Title
SAM2	-	-	-	77.9	SAM 2: Segment Anything in Images and Videos
Cutie+ (base, MEGA)	75.8	17.9	67.6	71.7	Putting the Object Back into Video Object Segmentation
Cutie+ (small, MEGA)	74.5	20.6	66.0	70.3	Putting the Object Back into Video Object Segmentation
Cutie (base, MEGA)	74.1	36.4	65.8	69.9	Putting the Object Back into Video Object Segmentation
Cutie (small, MEGA)	72.9	45.5	64.3	68.6	Putting the Object Back into Video Object Segmentation
Cutie (base, with mose)	72.3	36.4	64.2	68.3	Putting the Object Back into Video Object Segmentation
Cutie (small, with mose)	71.7	45.5	63.1	67.4	Putting the Object Back into Video Object Segmentation
DEVA (with OVIS)	70.8	25.3	62.3	66.5	Tracking Anything with Decoupled Video Segmentation
Cutie (base)	67.9	36.4	60.0	64.0	Putting the Object Back into Video Object Segmentation
Cutie (small)	66.2	45.5	58.2	62.2	Putting the Object Back into Video Object Segmentation
DEVA (no OVIS)	64.3	25.3	55.8	60.0	Tracking Anything with Decoupled Video Segmentation
DeAOT	63.8	-	55.1	59.4	Decoupling Features in Hierarchical Propagation for Video Object Segmentation
XMem	62.0	-	53.3	57.6	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AOT	61.3	-	53.1	57.2	Associating Objects with Transformers for Video Object Segmentation
SWEM	54.9	-	46.8	50.9	SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
STCN	55.0	-	46.6	50.8	Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
RDE	52.9	-	44.6	48.8	Recurrent Dynamic Embedding for Video Object Segmentation

0 of 17 row(s) selected.

Semi Supervised Video Object Segmentation On 21 | SOTA | HyperAI초신경