Referring Expression Segmentation On Refcoco 5

评估指标

Overall IoU

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
MLCD-Seg-7B	75.6	Multi-label Cluster Discrimination for Visual Representation Learning
HyperSeg	75.2	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
DETRIS	70.2	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
EVF-SAM	70.1	EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
C3VG	68.95	Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
UniLSeg-100	68.15	Universal Segmentation at Arbitrary Granularity with Language Instruction
UniLSeg-20	66.99	Universal Segmentation at Arbitrary Granularity with Language Instruction
UNINEXT-H	66.22	Universal Instance Perception as Object Discovery and Retrieval
GROUNDHOG	64.9	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
SafaRi-B	64.88	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
MaskRIS (Swin-B, combined DB)	62.83	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
PolyFormer-L	61.87	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
MaskRIS (Swin-B)	59.39	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
PolyFormer-B	59.33	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
MagNet	58.14	Mask Grounding for Referring Image Segmentation
ReLA	57.65	GRES: Generalized Referring Expression Segmentation
VLT	56.92	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
MaIL	56.06	MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation	-
LAVT	55.1	LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
CRIS	53.68	CRIS: CLIP-Driven Referring Image Segmentation

0 of 29 row(s) selected.