Video Instance Segmentation on OVIS validation

Metric: AR1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	AR1▼	Extra Data	Paper	Date↕	Code
1	CAVIS(VIT-L, Offline)	21.2	Yes	Context-Aware Video Instance Segmentation	2024-07-03	Code
2	DVIS++(VIT-L, Online)	20.8	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
3	DVIS(Swin-L, Offline)	19.4	No	DVIS: Decoupled Video Instance Segmentation Fram...	2023-06-06	Code
4	DVIS(Swin-L, Online)	19.4	No	DVIS: Decoupled Video Instance Segmentation Fram...	2023-06-06	Code
5	NOVIS (Swin-L)	19.4	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
6	GRAtt-VIS (Swin-L)	19.2	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
7	RefineVIS (Swin-L, offline)	19.1	Yes	RefineVIS: Video Instance Segmentation with Temp...	2023-06-07	-
8	GenVIS (Swin-L)	18.9	Yes	A Generalized Framework for Video Instance Segme...	2022-11-16	Code
9	ROVIS (Swin-L)	18.4	No	Robust Online Video Instance Segmentation with T...	2022-11-16	Code
10	MDQE(SwinL)	18.3	No	MDQE: Mining Discriminative Query Embeddings to ...	2023-03-25	Code
11	MinVIS (Swin-L)	18.1	No	MinVIS: A Minimal Video Instance Segmentation Fr...	2022-08-03	Code
12	TarViS (Swin-L)	18	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
13	IDOL (Swin-L)	17.9	No	In Defense of Online Models for Video Instance S...	2022-07-21	Code
14	DVIS++(R50, Offline)	16.8	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
15	GRAtt-VIS (ResNet-50)	16.8	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
16	DeVIS (Swin-L)	16.6	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
17	TarViS (Swin-T)	16.1	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
18	TarViS (ResNet-50)	15.9	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
19	DVIS++(R50, Online)	15.8	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
20	NOVIS (ResNet-50)	15.7	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
21	Tube-Link(ResNet-50)	15.5	No	Tube-Link: A Flexible Cross Tube Framework for U...	2023-03-22	Code
22	IDOL (ResNet-50)	15	No	In Defense of Online Models for Video Instance S...	2022-07-21	Code
23	VITA (Swin-L)	14.9	Yes	VITA: Video Instance Segmentation via Object Tok...	2022-06-09	Code
24	InstanceFormer (Swin-L)	12.9	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
25	DeVIS (ResNet-50)	12	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
26	InstanceFormer(ResNet-50)	12	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
27	Mask2Former-VIS	9.9	No	Mask2Former for Video Instance Segmentation	2021-12-20	Code
28	STMask(R101-DCN-FPN)	8.4	No	Spatial Feature Calibration and Temporal Fusion ...	2021-04-06	Code

#1CAVIS(VIT-L, Offline)SOTA
21.2
AR1· Extra Data· 2024-07-03
Context-Aware Video Instance Segmentation Code
#2DVIS++(VIT-L, Online)SOTA
20.8
AR1· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#3DVIS(Swin-L, Offline)SOTA
19.4
AR1· 2023-06-06
DVIS: Decoupled Video Instance Segmentation Framework Code
#4DVIS(Swin-L, Online)
19.4
AR1· 2023-06-06
DVIS: Decoupled Video Instance Segmentation Framework Code
#5NOVIS (Swin-L)
19.4
AR1· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#6GRAtt-VIS (Swin-L)SOTA
19.2
AR1· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#7RefineVIS (Swin-L, offline)
19.1
AR1· Extra Data· 2023-06-07
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
#8GenVIS (Swin-L)SOTA
18.9
AR1· Extra Data· 2022-11-16
A Generalized Framework for Video Instance Segmentation Code
#9ROVIS (Swin-L)
18.4
AR1· 2022-11-16
Robust Online Video Instance Segmentation with Track Queries Code
#10MDQE(SwinL)
18.3
AR1· 2023-03-25
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos Code
#11MinVIS (Swin-L)SOTA
18.1
AR1· 2022-08-03
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training Code
#12TarViS (Swin-L)
18
AR1· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#13IDOL (Swin-L)SOTA
17.9
AR1· 2022-07-21
In Defense of Online Models for Video Instance Segmentation Code
#14DVIS++(R50, Offline)
16.8
AR1· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#15GRAtt-VIS (ResNet-50)
16.8
AR1· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#16DeVIS (Swin-L)
16.6
AR1· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#17TarViS (Swin-T)
16.1
AR1· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#18TarViS (ResNet-50)
15.9
AR1· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#19DVIS++(R50, Online)
15.8
AR1· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#20NOVIS (ResNet-50)
15.7
AR1· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#21Tube-Link(ResNet-50)
15.5
AR1· 2023-03-22
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation Code
#22IDOL (ResNet-50)
15
AR1· 2022-07-21
In Defense of Online Models for Video Instance Segmentation Code
#23VITA (Swin-L)SOTA
14.9
AR1· Extra Data· 2022-06-09
VITA: Video Instance Segmentation via Object Token Association Code
#24InstanceFormer (Swin-L)
12.9
AR1· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#25DeVIS (ResNet-50)
12
AR1· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#26InstanceFormer(ResNet-50)
12
AR1· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#27Mask2Former-VISSOTA
9.9
AR1· 2021-12-20
Mask2Former for Video Instance Segmentation Code
#28STMask(R101-DCN-FPN)SOTA
8.4
AR1· 2021-04-06
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation Code