Referring Expression Segmentation On Refcoco 4

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
HyperSeg	83.5	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
MLCD-Seg-7B	82.9	Multi-label Cluster Discrimination for Visual Representation Learning
DETRIS	78.6	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
EVF-SAM	78.3	EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
UniLSeg-100	78.29	Universal Segmentation at Arbitrary Granularity with Language Instruction
C3VG	77.96	Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
UniLSeg-20	77.02	Universal Segmentation at Arbitrary Granularity with Language Instruction
UNINEXT-H	76.42	Universal Instance Perception as Object Discovery and Retrieval
MaskRIS (Swin-B, combined DB)	75.15	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
GROUNDHOG	75.0	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
PolyFormer-L	74.56	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
SafaRi-B	74.53	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
MaskRIS (Swin-B)	74.46	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
PolyFormer-B	72.89	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
MagNet	71.32	Mask Grounding for Referring Image Segmentation
ReLA	71.02	GRES: Generalized Referring Expression Segmentation
VLT	68.43	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
LAVT	68.38	LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
CRIS	68.08	CRIS: CLIP-Driven Referring Image Segmentation
MaIL	65.92	MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation	-

0 of 29 row(s) selected.