Video Instance Segmentation on OVIS validation

Metric: AP75 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	AP75▼	Extra Data	Paper	Date↕	Code
1	CAVIS(VIT-L, Offline)	63.5	Yes	Context-Aware Video Instance Segmentation	2024-07-03	Code
2	DVIS-DAQ(VIT-L, Offline)	62.9	Yes	DVIS-DAQ: Improving Video Segmentation via Dynam...	2024-03-29	Code
3	DVIS++(VIT-L,Offline)	58.5	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
4	GLEE-Pro	55.5	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
5	DVIS++(VIT-L, Online)	55	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
6	DVIS(Swin-L, Offline)	53	No	DVIS: Decoupled Video Instance Segmentation Fram...	2023-06-06	Code
7	UNINEXT (ViT-H, Online)	52.2	Yes	Universal Instance Perception as Object Discover...	2023-03-12	Code
8	DVIS(Swin-L, Online)	49.2	No	DVIS: Decoupled Video Instance Segmentation Fram...	2023-06-06	Code
9	RefineVIS (Swin-L, offline)	48.4	Yes	RefineVIS: Video Instance Segmentation with Temp...	2023-06-07	-
10	GRAtt-VIS (Swin-L)	47.8	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
11	GenVIS (Swin-L)	47.8	Yes	A Generalized Framework for Video Instance Segme...	2022-11-16	Code
12	CTVIS (Swin-L)	47.5	Yes	CTVIS: Consistent Training for Online Video Inst...	2023-07-24	Code
13	IDOL (Swin-L)	45.2	No	In Defense of Online Models for Video Instance S...	2022-07-21	Code
14	TarViS (Swin-L)	44.6	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
15	MDQE(SwinL)	44.3	No	MDQE: Mining Discriminative Query Embeddings to ...	2023-03-25	Code
16	NOVIS (Swin-L)	43.8	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
17	ROVIS (Swin-L)	42.6	No	Robust Online Video Instance Segmentation with T...	2022-11-16	Code
18	MinVIS (Swin-L)	41.3	No	MinVIS: A Minimal Video Instance Segmentation Fr...	2022-08-03	Code
19	DVIS++(R50, Offline)	40.9	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
20	BoxVIS(Swin-L & Box-sup)	39.9	No	BoxVIS: Video Instance Segmentation with Box Ann...	2023-03-26	Code
21	DeVIS (Swin-L)	38.3	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
22	DVIS++(R50, Online)	37.3	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
23	GRAtt-VIS (ResNet-50)	36.8	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
24	UNINEXT (ResNet-50, Online)	35.6	Yes	Universal Instance Perception as Object Discover...	2023-03-12	Code
25	CTVIS (ResNet-50)	34.9	Yes	CTVIS: Consistent Training for Online Video Inst...	2023-07-24	Code
26	TarViS (Swin-T)	34.4	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
27	NOVIS (ResNet-50)	32.6	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
28	TarViS (ResNet-50)	30.4	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
29	Tube-Link(ResNet-50)	30.2	No	Tube-Link: A Flexible Cross Tube Framework for U...	2023-03-22	Code
30	IDOL (ResNet-50)	30	No	In Defense of Online Models for Video Instance S...	2022-07-21	Code
31	VITA (Swin-L)	24.9	Yes	VITA: Video Instance Segmentation via Object Tok...	2022-06-09	Code
32	InstanceFormer (Swin-L)	21.61	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
33	DeVIS (ResNet-50)	20.8	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
34	InstanceFormer(ResNet-50)	18.1	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
35	CrossVIS (ResNet-50, calibration)	16.9	No	Crossover Learning for Fast Online Video Instanc...	2021-04-13	Code
36	STMask(R101-DCN-FPN)	15.2	No	Spatial Feature Calibration and Temporal Fusion ...	2021-04-06	Code
37	TeViT (ResNet-50)	15	No	Temporally Efficient Vision Transformer for Vide...	2022-04-18	Code
38	Mask2Former-VIS	14.1	No	Mask2Former for Video Instance Segmentation	2021-12-20	Code
39	D2Conv3D (ResNet-50)	13.7	No	-	-	Code
40	STC (ResNet-50)	13.4	No	STC: Spatio-Temporal Contrastive Learning for Vi...	2022-02-08	-
41	CMaskTrack R-CNN (ResNet-50)	13.1	No	Occluded Video Instance Segmentation: A Benchmark	2021-02-02	Code
42	CSipMask (ResNet-50)	12.5	No	Occluded Video Instance Segmentation: A Benchmark	2021-02-02	Code
43	CrossVIS (ResNet-50)	12.1	No	Crossover Learning for Fast Online Video Instanc...	2021-04-13	Code

#1CAVIS(VIT-L, Offline)SOTA
63.5
AP75· Extra Data· 2024-07-03
Context-Aware Video Instance Segmentation Code
#2DVIS-DAQ(VIT-L, Offline)SOTA
62.9
AP75· Extra Data· 2024-03-29
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries Code
#3DVIS++(VIT-L,Offline)SOTA
58.5
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#4GLEE-ProSOTA
55.5
AP75· Extra Data· 2023-12-14
General Object Foundation Model for Images and Videos at Scale Code
#5DVIS++(VIT-L, Online)
55
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#6DVIS(Swin-L, Offline)SOTA
53
AP75· 2023-06-06
DVIS: Decoupled Video Instance Segmentation Framework Code
#7UNINEXT (ViT-H, Online)SOTA
52.2
AP75· Extra Data· 2023-03-12
Universal Instance Perception as Object Discovery and Retrieval Code
#8DVIS(Swin-L, Online)
49.2
AP75· 2023-06-06
DVIS: Decoupled Video Instance Segmentation Framework Code
#9RefineVIS (Swin-L, offline)
48.4
AP75· Extra Data· 2023-06-07
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
#10GRAtt-VIS (Swin-L)
47.8
AP75· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#11GenVIS (Swin-L)SOTA
47.8
AP75· Extra Data· 2022-11-16
A Generalized Framework for Video Instance Segmentation Code
#12CTVIS (Swin-L)
47.5
AP75· Extra Data· 2023-07-24
CTVIS: Consistent Training for Online Video Instance Segmentation Code
#13IDOL (Swin-L)SOTA
45.2
AP75· 2022-07-21
In Defense of Online Models for Video Instance Segmentation Code
#14TarViS (Swin-L)
44.6
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#15MDQE(SwinL)
44.3
AP75· 2023-03-25
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos Code
#16NOVIS (Swin-L)
43.8
AP75· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#17ROVIS (Swin-L)
42.6
AP75· 2022-11-16
Robust Online Video Instance Segmentation with Track Queries Code
#18MinVIS (Swin-L)
41.3
AP75· 2022-08-03
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training Code
#19DVIS++(R50, Offline)
40.9
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#20BoxVIS(Swin-L & Box-sup)
39.9
AP75· 2023-03-26
BoxVIS: Video Instance Segmentation with Box Annotations Code
#21DeVIS (Swin-L)
38.3
AP75· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#22DVIS++(R50, Online)
37.3
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#23GRAtt-VIS (ResNet-50)
36.8
AP75· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#24UNINEXT (ResNet-50, Online)
35.6
AP75· Extra Data· 2023-03-12
Universal Instance Perception as Object Discovery and Retrieval Code
#25CTVIS (ResNet-50)
34.9
AP75· Extra Data· 2023-07-24
CTVIS: Consistent Training for Online Video Instance Segmentation Code
#26TarViS (Swin-T)
34.4
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#27NOVIS (ResNet-50)
32.6
AP75· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#28TarViS (ResNet-50)
30.4
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#29Tube-Link(ResNet-50)
30.2
AP75· 2023-03-22
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation Code
#30IDOL (ResNet-50)
30
AP75· 2022-07-21
In Defense of Online Models for Video Instance Segmentation Code
#31VITA (Swin-L)SOTA
24.9
AP75· Extra Data· 2022-06-09
VITA: Video Instance Segmentation via Object Token Association Code
#32InstanceFormer (Swin-L)
21.61
AP75· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#33DeVIS (ResNet-50)
20.8
AP75· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#34InstanceFormer(ResNet-50)
18.1
AP75· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#35CrossVIS (ResNet-50, calibration)SOTA
16.9
AP75· 2021-04-13
Crossover Learning for Fast Online Video Instance Segmentation Code
#36STMask(R101-DCN-FPN)SOTA
15.2
AP75· 2021-04-06
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation Code
#37TeViT (ResNet-50)
15
AP75· 2022-04-18
Temporally Efficient Vision Transformer for Video Instance Segmentation Code
#38Mask2Former-VIS
14.1
AP75· 2021-12-20
Mask2Former for Video Instance Segmentation Code
#39D2Conv3D (ResNet-50)
13.7
AP75
No paperCode
#40STC (ResNet-50)
13.4
AP75· 2022-02-08
STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation
#41CMaskTrack R-CNN (ResNet-50)SOTA
13.1
AP75· 2021-02-02
Occluded Video Instance Segmentation: A Benchmark Code
#42CSipMask (ResNet-50)
12.5
AP75· 2021-02-02
Occluded Video Instance Segmentation: A Benchmark Code
#43CrossVIS (ResNet-50)
12.1
AP75· 2021-04-13
Crossover Learning for Fast Online Video Instance Segmentation Code