Referring Expression Segmentation on DAVIS 2017 (val)

Metric: J&F 1st frame (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	J&F 1st frame▼	Extra Data	Paper	Date↕	Code
1	UNINEXT-H	72.5	Yes	Universal Instance Perception as Object Discover...	2023-03-12	Code
2	HyperSeg	71.2	Yes	HyperSeg: Towards Universal Visual Segmentation ...	2024-11-26	Code
3	DEVA (ReferFormer)	66.3	Yes	Tracking Anything with Decoupled Video Segmentat...	2023-09-07	Code
4	HTR	65.6	Yes	Temporally Consistent Referring Video Object Seg...	2024-03-28	Code
5	SgMg	63.3	Yes	Spectrum-guided Multi-granularity Referring Vide...	2023-07-25	Code
6	SafaRi-B	61.3	No	SafaRi:Adaptive Sequence Transformer for Weakly ...	2024-07-02	-
7	ReferFormer	61.1	Yes	Language as Queries for Referring Video Object S...	2022-01-03	Code
8	PolyFormer-B	60.9	Yes	PolyFormer: Referring Image Segmentation as Sequ...	2023-02-14	Code
9	URVOS + Refer-Youtube-VOS + ft. DAVIS	51.63	Yes	-	-	Code
10	HINet	50.2	No	-	-	-
11	URVOS + Refer-Youtube-VOS	46.85	Yes	-	-	Code
12	RefVOS + SynthRef-YouTube-VIS	45.3	Yes	SynthRef: Generation of Synthetic Referring Expr...	2021-06-08	Code
13	RefVOS	45.1	No	RefVOS: A Closer Look at Referring Expressions f...	2020-10-01	Code
14	RefVOS	44.5	No	RefVOS: A Closer Look at Referring Expressions f...	2020-10-01	Code
15	URVOS	44.1	No	-	-	Code
16	Khoreva et al.	39.3	No	Video Object Segmentation with Language Referrin...	2018-03-21	-

#1UNINEXT-HSOTA
72.5
J&F 1st frame· Extra Data· 2023-03-12
Universal Instance Perception as Object Discovery and Retrieval Code
#2HyperSeg
71.2
J&F 1st frame· Extra Data· 2024-11-26
HyperSeg: Towards Universal Visual Segmentation with Large Language Model Code
#3DEVA (ReferFormer)
66.3
J&F 1st frame· Extra Data· 2023-09-07
Tracking Anything with Decoupled Video Segmentation Code
#4HTR
65.6
J&F 1st frame· Extra Data· 2024-03-28
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory Code
#5SgMg
63.3
J&F 1st frame· Extra Data· 2023-07-25
Spectrum-guided Multi-granularity Referring Video Object Segmentation Code
#6SafaRi-B
61.3
J&F 1st frame· 2024-07-02
SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation
#7ReferFormerSOTA
61.1
J&F 1st frame· Extra Data· 2022-01-03
Language as Queries for Referring Video Object Segmentation Code
#8PolyFormer-B
60.9
J&F 1st frame· Extra Data· 2023-02-14
PolyFormer: Referring Image Segmentation as Sequential Polygon Generation Code
#9URVOS + Refer-Youtube-VOS + ft. DAVIS
51.63
J&F 1st frame· Extra Data
No paperCode
#10HINet
50.2
J&F 1st frame
No paper
#11URVOS + Refer-Youtube-VOS
46.85
J&F 1st frame· Extra Data
No paperCode
#12RefVOS + SynthRef-YouTube-VISSOTA
45.3
J&F 1st frame· Extra Data· 2021-06-08
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation Code
#13RefVOSSOTA
45.1
J&F 1st frame· 2020-10-01
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation Code
#14RefVOS
44.5
J&F 1st frame· 2020-10-01
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation Code
#15URVOS
44.1
J&F 1st frame
No paperCode
#16Khoreva et al.SOTA
39.3
J&F 1st frame· 2018-03-21
Video Object Segmentation with Language Referring Expressions