List your company
ResearchFormerly WizWand

Referring Image Segmentation on G-Ref (test)

80.54IoUUniLSeg-100
45.606454.675763.74572.8143Nov 30, 2021Apr 23, 2022Sep 14, 2022Feb 5, 2023Jun 29, 2023Nov 20, 2023Apr 12, 2024
Updated 8mo ago

Evaluation results

MethodLinks
UniLSeg-100Vision Backbone=Swin-B2023.1280.54
UniLSeg-20Vision Backbone=Swin-B2023.1279.47
VATEX_jointExternal Datasets=RefCOCO(+/g) (368K), Backbone=Swin-B2024.0476.4
UniNextVision Backbone=ConvNext-L2023.1273.68
VATEXVisual Backbone=Swin-B, Textual Backbone=CLIP2024.0470.58
VATEX_G-RefExternal Datasets=G-Ref (85K), Backbone=Swin-B2024.0470.58
PolyFormer-BExternal Datasets=RefCOCO(+/g) (368K)2024.0469.88
PolyFormerVision Backbone=Swin-B2023.1269.05
LISA-7BVisual Backbone=ViT-H SAM, Textual Backbone=Vicuna-7B2024.0468.5
RefTRExternal Datasets=Visual Genome (5.4M) & Flickr30k-entities (158K)2024.0467.39
VLTVisual Backbone=Swin-B, Textual Backbone=BERT2024.0466.22
GRESVision Backbone=Swin-B2023.1265.97
SeqTRExternal Datasets=Visual Genome (5.4M) & Flickr30k-entities (158K)2024.0465.74
VG-LAWVisual Backbone=ViT-B, Textual Backbone=BERT2024.0465.13
LAVTVisual Backbone=Swin-B, Textual Backbone=BERT2024.0463.62
CM-MaskSDVisual Backbone=CLIP-ViT-B, Textual Backbone=CLIP2024.0462.69
LAVTVision Backbone=Swin-B2023.1262.09
CRISBackbone=ResNet-1012021.1160.36
CRISVisual Backbone=ResNet-101, Textual Backbone=CLIP2024.0460.36
CRISVision Backbone=ResNet1012023.1260.36
CRISBackbone=ResNet-502021.1159.39
CRISVision Backbone=ResNet502023.1259.39
VLTBackbone=DarkNet-532021.1156.65
VLTVision Backbone=DarkNet532023.1256.65
LTSBackbone=DarkNet-532021.1154.25
LTSVision Backbone=DarkNet532023.1254.25
CGANBackbone=DarkNet-532021.1151.69
CGANVision Backbone=DarkNet532023.1251.69
MCNBackbone=DarkNet-532021.1149.4
MCNVision Backbone=DarkNet532023.1249.4
MAttNetBackbone=ResNet-1012021.1148.61
NMTreeBackbone=ResNet-1012021.1147.88
Lang2SegBackbone=ResNet-1012021.1146.95