HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Referring Expression Segmentation On Refcocog 1

평가 지표

Overall IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Overall IoU	Paper Title	Repository
GROUNDHOG	74.6	GROUNDHOG: Grounding Large Language Models to Holistic Segmentation	-
SafaRi-B	71.06	SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation	-
UniLSeg-20	79.47	Universal Segmentation at Arbitrary Granularity with Language Instruction
EVF-SAM	77.4	EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
MaskRIS (Swin-B)	66.5	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
VATEX	-	Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
PolyFormer-L	70.19	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
PolyFormer-B	69.05	PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
VLT (Darknet53)	56.65	Vision-Language Transformer and Query Generation for Referring Segmentation
MagNet	66.03	Mask Grounding for Referring Image Segmentation
DETRIS	75.3	Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
UniLSeg-100	80.54	Universal Segmentation at Arbitrary Granularity with Language Instruction
MaskRIS (Swin-B, combined DB)	71.09	MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
HyperSeg	78.9	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
C3VG	76.39	Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
LAVT (Swin-B)	62.09	LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
MLCD-Seg-7B	80.5	Multi-label Cluster Discrimination for Visual Representation Learning

0 of 17 row(s) selected.