Video on DAVIS 2016

Metric: F-Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	F-Score▼	Extra Data	Paper	Date↕	Code
1	AOC-MF (val)	94.7	No	Towards Robust Video Object Segmentation with Ad...	2022-07-02	Code
2	XMem (BL30K, MS)	94.4	No	XMem: Long-Term Video Object Segmentation with a...	2022-07-14	Code
3	ISVOS (BL30K, MS)	94.2	No	Look Before You Match: Instance Understanding Ma...	2022-12-13	-
4	BATMAN (val)	94.2	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
5	RPCMVOS (val)	94	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
6	XMem	92.7	No	XMem: Long-Term Video Object Segmentation with a...	2022-07-14	Code
7	MobileVOS (val)	92.6	No	MobileVOS: Real-Time Video Object Segmentation C...	2023-03-14	-
8	STCN (val)	92.5	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
9	AOT (val)	92.1	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
10	KMN (val)	91.5	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
11	LCM (val)	91.4	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
12	TransVOS (val)	91.2	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
13	CFBI+ (val)	91.1	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
14	CFBI (val)	90.5	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
15	ViTAE-T-Stage	90.4	No	ViTAE: Vision Transformer Advanced by Exploring ...	2021-06-07	Code
16	STM (val)	89.9	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
17	RMN (val)	88.7	No	BATMAN: Bilateral Attention Transformer in Motio...	2022-08-01	-
18	3DC-Seg	84.7	Yes	Making a Case for 3D Convolutions for Object Seg...	2020-08-26	Code
19	DFNet	81.8	No	Learning Discriminative Feature with CRF for Uns...	2020-08-04	-

#1AOC-MF (val)SOTA
94.7
F-Score· 2022-07-02
Towards Robust Video Object Segmentation with Adaptive Object Calibration Code
#2XMem (BL30K, MS)
94.4
F-Score· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model Code
#3ISVOS (BL30K, MS)
94.2
F-Score· 2022-12-13
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
#4BATMAN (val)
94.2
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#5RPCMVOS (val)
94
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#6XMem
92.7
F-Score· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model Code
#7MobileVOS (val)
92.6
F-Score· 2023-03-14
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation
#8STCN (val)
92.5
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#9AOT (val)
92.1
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#10KMN (val)
91.5
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#11LCM (val)
91.4
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#12TransVOS (val)
91.2
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#13CFBI+ (val)
91.1
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#14CFBI (val)
90.5
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#15ViTAE-T-StageSOTA
90.4
F-Score· 2021-06-07
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias Code
#16STM (val)
89.9
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#17RMN (val)
88.7
F-Score· 2022-08-01
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
#183DC-SegSOTA
84.7
F-Score· Extra Data· 2020-08-26
Making a Case for 3D Convolutions for Object Segmentation in Videos Code
#19DFNetSOTA
81.8
F-Score· 2020-08-04
Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation