Referring Expression Segmentation On Refcoco

평가 지표

Overall IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Overall IoU	Paper Title	Repository
MaskRIS (Swin-B, combined DB)	78.71	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
BRINet	61.35	Bi-Directional Relationship Inferring Network for Referring Image Segmentation	-
VLT	65.65	Vision-Language Transformer and Query Generation for Referring Segmentation
SHNet	65.32	Comprehensive Multi-Modal Interactions for Referring Image Segmentation
CRIS	70.47	CRIS: CLIP-Driven Referring Image Segmentation
SafaRi-B	77.21	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
CPMC	61.36	Referring Image Segmentation via Cross-Modal Progressive Comprehension
LANG2SEG	58.90	Referring Expression Object Segmentation with Caption-Aware Consistency
MaskRIS (Swin-B)	76.49	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
EVF-SAM	82.1	EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
CMSA	58.32	Cross-Modal Self-Attention Network for Referring Image Segmentation
MLCD-Seg-7B	83.6	Multi-label Cluster Discrimination for Visual Representation Learning
HIPIE	82.8	Hierarchical Open-vocabulary Universal Image Segmentation
PSALM	83.6	PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
PolyFormer-L	75.96	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
UniLSeg-100	81.74	Universal Segmentation at Arbitrary Granularity with Language Instruction
GROUNDHOG	78.5	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
DETRIS	81.0	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
RefVOS with BERT + MLM loss	59.45	RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation
RefVOS with BERT Pre-train	58.65	RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation

0 of 35 row(s) selected.