Video Instance Segmentation on YouTube-VIS 2021

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)	73.2	Yes	Context-Aware Video Instance Segmentation	2024-07-03	Code
2	DVIS-DAQ(VIT-L, Offline)	72.2	Yes	DVIS-DAQ: Improving Video Segmentation via Dynam...	2024-03-29	Code
3	DVIS++(VIT-L, Offline)	71.5	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
4	DVIS++(VIT-L, Online)	70.2	Yes	DVIS++: Improved Decoupled Framework for Univers...	2023-12-20	Code
5	RefineVIS (Swin-L, online)	68.5	Yes	RefineVIS: Video Instance Segmentation with Temp...	2023-06-07	-
6	DVIS(Swin-L)	68.4	Yes	DVIS: Decoupled Video Instance Segmentation Fram...	2023-06-06	Code
7	TarViS (Swin-L)	67.6	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
8	GRAtt-VIS (Swin-L)	67.1	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
9	GenVIS (Swin-L)	66.5	Yes	A Generalized Framework for Video Instance Segme...	2022-11-16	Code
10	NOVIS (Swin-L)	66.5	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
11	Tube-Link(Swin-L)	64.3	No	Tube-Link: A Flexible Cross Tube Framework for U...	2023-03-22	Code
12	IDOL (Swin-L)	63.5	No	In Defense of Online Models for Video Instance S...	2022-07-21	Code
13	UniVS(Swin-L)	63.3	Yes	UniVS: Unified and Universal Video Segmentation ...	2024-02-28	Code
14	MinVIS (Swin-L)	62	No	MinVIS: A Minimal Video Instance Segmentation Fr...	2022-08-03	Code
15	MDQE(Swin-L)	61.7	No	MDQE: Mining Discriminative Query Embeddings to ...	2023-03-25	Code
16	VITA (Swin-L)	61	Yes	VITA: Video Instance Segmentation via Object Tok...	2022-06-09	Code
17	DeVIS (Swin-L)	59.8	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
18	BoxVIS(Swin-L & Box-sup)	59.6	No	BoxVIS: Video Instance Segmentation with Box Ann...	2023-03-26	Code
19	InstanceFormer (Swin-L)	56.9	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
20	TarViS (Swin-T)	56.6	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
21	TarViS (ResNet-50)	53.2	Yes	TarViS: A Unified Approach for Target-based Vide...	2023-01-06	Code
22	GRAtt-VIS (ResNet-50)	53.1	Yes	GRAtt-VIS: Gated Residual Attention for Auto Rec...	2023-05-26	Code
23	NOVIS (ResNet-50)	50	Yes	NOVIS: A Case for End-to-End Near-Online Video I...	2023-08-29	-
24	DeVIS (ResNet-50)	46.6	No	DeVIS: Making Deformable Transformers Work for V...	2022-07-22	Code
25	InstanceFormer (ResNet-50)	43.7	Yes	InstanceFormer: An Online Video Instance Segment...	2022-08-22	Code
26	STMask(R101-DCN-FPN)	38	No	Spatial Feature Calibration and Temporal Fusion ...	2021-04-06	Code

#1CAVIS(VIT-L, Offline)SOTA
73.2
AP75· Extra Data· 2024-07-03
Context-Aware Video Instance Segmentation Code
#2DVIS-DAQ(VIT-L, Offline)SOTA
72.2
AP75· Extra Data· 2024-03-29
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries Code
#3DVIS++(VIT-L, Offline)SOTA
71.5
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#4DVIS++(VIT-L, Online)
70.2
AP75· Extra Data· 2023-12-20
DVIS++: Improved Decoupled Framework for Universal Video Segmentation Code
#5RefineVIS (Swin-L, online)SOTA
68.5
AP75· Extra Data· 2023-06-07
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
#6DVIS(Swin-L)SOTA
68.4
AP75· Extra Data· 2023-06-06
DVIS: Decoupled Video Instance Segmentation Framework Code
#7TarViS (Swin-L)SOTA
67.6
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#8GRAtt-VIS (Swin-L)
67.1
AP75· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#9GenVIS (Swin-L)SOTA
66.5
AP75· Extra Data· 2022-11-16
A Generalized Framework for Video Instance Segmentation Code
#10NOVIS (Swin-L)
66.5
AP75· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#11Tube-Link(Swin-L)
64.3
AP75· 2023-03-22
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation Code
#12IDOL (Swin-L)SOTA
63.5
AP75· 2022-07-21
In Defense of Online Models for Video Instance Segmentation Code
#13UniVS(Swin-L)
63.3
AP75· Extra Data· 2024-02-28
UniVS: Unified and Universal Video Segmentation with Prompts as Queries Code
#14MinVIS (Swin-L)
62
AP75· 2022-08-03
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training Code
#15MDQE(Swin-L)
61.7
AP75· 2023-03-25
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos Code
#16VITA (Swin-L)SOTA
61
AP75· Extra Data· 2022-06-09
VITA: Video Instance Segmentation via Object Token Association Code
#17DeVIS (Swin-L)
59.8
AP75· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#18BoxVIS(Swin-L & Box-sup)
59.6
AP75· 2023-03-26
BoxVIS: Video Instance Segmentation with Box Annotations Code
#19InstanceFormer (Swin-L)
56.9
AP75· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#20TarViS (Swin-T)
56.6
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#21TarViS (ResNet-50)
53.2
AP75· Extra Data· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation Code
#22GRAtt-VIS (ResNet-50)
53.1
AP75· Extra Data· 2023-05-26
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation Code
#23NOVIS (ResNet-50)
50
AP75· Extra Data· 2023-08-29
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
#24DeVIS (ResNet-50)
46.6
AP75· 2022-07-22
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation Code
#25InstanceFormer (ResNet-50)
43.7
AP75· Extra Data· 2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework Code
#26STMask(R101-DCN-FPN)SOTA
38
AP75· 2021-04-06
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation Code