Referring Expression Segmentation On Refcoco

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	84.8	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
MLCD-Seg-7B	83.6	Multi-label Cluster Discrimination for Visual Representation Learning
PSALM	83.6	PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
HIPIE	82.8	Hierarchical Open-vocabulary Universal Image Segmentation
UNINEXT-H	82.19	Universal Instance Perception as Object Discovery and Retrieval
EVF-SAM	82.1	EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
UniLSeg-100	81.74	Universal Segmentation at Arbitrary Granularity with Language Instruction
DETRIS	81.0	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
C3VG	80.89	Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
GLEE-Pro	80.0	General Object Foundation Model for Images and Videos at Scale
MaskRIS (Swin-B, combined DB)	78.71	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
GROUNDHOG	78.5	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
SafaRi-B	77.21	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
MaskRIS (Swin-B)	76.49	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
PolyFormer-L	75.96	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
MagNet	75.24	Mask Grounding for Referring Image Segmentation
PolyFormer-B	74.82	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
ReLA	73.82	GRES: Generalized Referring Expression Segmentation
VPD	73.25	Unleashing Text-to-Image Diffusion Models for Visual Perception
VLT	72.96	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation

0 of 35 row(s) selected.