Referring Expression Segmentation On Refcoco 3

Metrics

Overall IoU

Results

Performance results of various models on this benchmark

Model Name	Overall IoU	Paper Title	Repository
VLT	63.53	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
CPMC	49.56	Referring Image Segmentation via Cross-Modal Progressive Comprehension
UniLSeg-20	72.70	Universal Segmentation at Arbitrary Granularity with Language Instruction
MagNet	66.16	Mask Grounding for Referring Image Segmentation
BRINet	48.57	Bi-Directional Relationship Inferring Network for Referring Image Segmentation	-
SafaRi-B	70.78	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
GLEE-Pro	69.6	General Object Foundation Model for Images and Videos at Scale
CMSA	43.76	Cross-Modal Self-Attention Network for Referring Image Segmentation
LAVT	62.14	LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
MaskRIS (Swin-B, combined DB)	70.26	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
CRIS	62.27	CRIS: CLIP-Driven Referring Image Segmentation
UNINEXT-H	72.47	Universal Instance Perception as Object Discovery and Retrieval
VLT	55.50	Vision-Language Transformer and Query Generation for Referring Segmentation
UniLSeg-100	73.18	Universal Segmentation at Arbitrary Granularity with Language Instruction
PolyFormer-L	69.33	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
ReLA	66.04	GRES: Generalized Referring Expression Segmentation
HyperSeg	79.0	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
GROUNDHOG	70.5	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
DETRIS	75.2	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
MaIL	62.23	MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation	-

0 of 31 row(s) selected.