Generalized Referring Expression Comprehension on gRefCOCO

Metric: Precision@(F1=1, IoU≥0.5) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Precision@(F1=1, IoU≥0.5)▼	Extra Data	Paper	Date↕	Code
1	SimVG-DB	62.1	No	SimVG: A Simple Framework for Visual Grounding w...	2024-09-26	Code
2	UNINEXT	58.2	No	Universal Instance Perception as Object Discover...	2023-03-12	Code
3	MDETR	41.5	No	MDETR -- Modulated Detection for End-to-End Mult...	2021-04-26	Code
4	VLT	36.6	No	Vision-Language Transformer and Query Generation...	2021-08-12	Code
5	MCN	28	No	Multi-task Collaborative Network for Joint Refer...	2020-03-19	Code

#1SimVG-DBSOTA
62.1
Precision@(F1=1, IoU≥0.5)· 2024-09-26
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion Code
#2UNINEXTSOTA
58.2
Precision@(F1=1, IoU≥0.5)· 2023-03-12
Universal Instance Perception as Object Discovery and Retrieval Code
#3MDETRSOTA
41.5
Precision@(F1=1, IoU≥0.5)· 2021-04-26
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding Code
#4VLT
36.6
Precision@(F1=1, IoU≥0.5)· 2021-08-12
Vision-Language Transformer and Query Generation for Referring Segmentation Code
#5MCNSOTA
28
Precision@(F1=1, IoU≥0.5)· 2020-03-19
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation Code