HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Referring Expression Segmentation On Refcoco

Metrics

Overall IoU

Results

Performance results of various models on this benchmark

Paper Title
HyperSeg84.8HyperSeg: Towards Universal Visual Segmentation with Large Language Model
MLCD-Seg-7B83.6Multi-label Cluster Discrimination for Visual Representation Learning
PSALM83.6PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
HIPIE82.8Hierarchical Open-vocabulary Universal Image Segmentation
UNINEXT-H82.19Universal Instance Perception as Object Discovery and Retrieval
EVF-SAM82.1EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
UniLSeg-10081.74Universal Segmentation at Arbitrary Granularity with Language Instruction
DETRIS81.0Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
C3VG80.89Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
GLEE-Pro80.0General Object Foundation Model for Images and Videos at Scale
MaskRIS (Swin-B, combined DB)78.71MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
GROUNDHOG78.5GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
SafaRi-B77.21SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation
MaskRIS (Swin-B)76.49MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
PolyFormer-L75.96PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
MagNet75.24Mask Grounding for Referring Image Segmentation
PolyFormer-B74.82PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
ReLA73.82GRES: Generalized Referring Expression Segmentation
VPD73.25Unleashing Text-to-Image Diffusion Models for Visual Perception
VLT72.96VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
0 of 35 row(s) selected.