Referring Expression Segmentation on RefCOCO+ val

Metric: Overall IoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	Overall IoU▼	Extra Data	Paper	Date↕	Code
1	MLCD-Seg-7B	79.4	Yes	Multi-label Cluster Discrimination for Visual Re...	2024-07-24	Code
2	DeRIS-L	79.01	No	DeRIS: Decoupling Perception and Cognition for E...	2025-07-02	Code
3	HyperSeg	79	Yes	HyperSeg: Towards Universal Visual Segmentation ...	2024-11-26	Code
4	EVF-SAM	76.5	Yes	EVF-SAM: Early Vision-Language Fusion for Text-P...	2024-06-28	Code
5	DETRIS	75.2	No	Densely Connected Parameter-Efficient Tuning for...	2025-01-15	Code
6	C3VG	74.68	No	Multi-task Visual Grounding with Coarse-to-Fine ...	2025-01-12	Code
7	HIPIE	73.9	Yes	Hierarchical Open-vocabulary Universal Image Seg...	2023-07-03	Code
8	UniLSeg-100	73.18	Yes	Universal Segmentation at Arbitrary Granularity ...	2023-12-04	Code
9	UniLSeg-20	72.7	Yes	Universal Segmentation at Arbitrary Granularity ...	2023-12-04	Code
10	SegAgent	72.49	No	SegAgent: Exploring Pixel Understanding Capabili...	2025-03-11	Code
11	UNINEXT-H	72.47	Yes	Universal Instance Perception as Object Discover...	2023-03-12	Code
12	SafaRi-B	70.78	No	SafaRi:Adaptive Sequence Transformer for Weakly ...	2024-07-02	-
13	GROUNDHOG	70.5	Yes	GROUNDHOG: Grounding Large Language Models to Ho...	2024-02-26	-
14	MaskRIS (Swin-B, combined DB)	70.26	No	MaskRIS: Semantic Distortion-aware Data Augmenta...	2024-11-28	Code
15	GLEE-Pro	69.6	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
16	PolyFormer-L	69.33	Yes	PolyFormer: Referring Image Segmentation as Sequ...	2023-02-14	Code
17	PolyFormer-B	67.64	Yes	PolyFormer: Referring Image Segmentation as Sequ...	2023-02-14	Code
18	MaskRIS (Swin-B)	67.54	No	MaskRIS: Semantic Distortion-aware Data Augmenta...	2024-11-28	Code
19	MagNet	66.16	No	Mask Grounding for Referring Image Segmentation	2023-12-19	Code
20	ReLA	66.04	No	GRES: Generalized Referring Expression Segmentat...	2023-06-01	Code
21	VLT	63.53	No	VLT: Vision-Language Transformer and Query Gener...	2022-10-28	Code
22	CRIS	62.27	No	CRIS: CLIP-Driven Referring Image Segmentation	2021-11-30	Code
23	MaIL	62.23	No	MaIL: A Unified Mask-Image-Language Trimodal Net...	2021-11-21	-
24	LAVT	62.14	No	LAVT: Language-Aware Vision Transformer for Refe...	2021-12-04	Code
25	VLT	55.5	No	Vision-Language Transformer and Query Generation...	2021-08-12	Code
26	SHNet	52.75	No	Comprehensive Multi-Modal Interactions for Refer...	2021-04-21	Code
27	CPMC	49.56	No	Referring Image Segmentation via Cross-Modal Pro...	2020-10-01	Code
28	BRINet	48.57	No	-	-	-
29	STEP (5-fold)	48.18	No	-	-	-
30	MattNet	46.67	No	MAttNet: Modular Attention Network for Referring...	2018-01-24	Code
31	RefVOS with BERT + MLM loss	44.71	No	RefVOS: A Closer Look at Referring Expressions f...	2020-10-01	Code
32	CMSA	43.76	No	Cross-Modal Self-Attention Network for Referring...	2019-04-09	Code