List your company
ResearchFormerly WizWand

Semantic Segmentation on PascalVOC

94.5mIoUOVSeg
7.03629.74352.4575.157Dec 1, 2023Apr 23, 2024Sep 15, 2024Feb 7, 2025Jul 2, 2025Nov 24, 2025Apr 18, 2026
Updated 6mo ago

Evaluation results

MethodLinks
OVSegEncoder=ViT-B/16, Model=CLIP, Pretraining=COCO-Stuff-171, Annotation=UM, Localization Annotation=true, Localization Fine-tuning=true2023.1294.5
DeepLabV32026.0485.7
RADIOv2.5-Hevaluation_protocol=linear probing2025.1285.65
RADIOv2.5-Levaluation_protocol=linear probing2025.1284.83
Lorentz (DeepLab-R101)Backbone=R1012026.0484.8
AMoEevaluation_protocol=linear probing2025.1284.4
CLIP-ESEncoder=ResNet101, Model=CLIP, Pretraining=COCO-Stuff-171, Annotation=IC, Localization Annotation=true, Localization Fine-tuning=true2023.1275
PACLEncoder=ViT-B/16, Model=CLIP, Pretraining=WIT-400M +CC12M, YFCC, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=true2023.1272.3
OpenSegEncoder=ENet-B7+FPN, Model=ALIGN, Pretraining=COCO, Loc. Narr, Annotation=IT, UM, Localization Annotation=true, Localization Fine-tuning=true2023.1272.2
OVSegmentorEncoder=ViT-B/16, Model=DINO, Pretraining=GCC, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=true2023.1253.8
SegCLIPEncoder=ViT-B/16, Model=CLIP, Pretraining=CC, COCOcap, Annotation=IT, ICap, Localization Annotation=false, Localization Fine-tuning=true2023.1252.6
GroupViTEncoder=ViT-S/16, Model=scratch, Pretraining=GCC+YFCC, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=true2023.1252.3
GEMEncoder=ViT-B/16, Model=MetaCLIP, Pretraining=metaclip-400M, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=false2023.1246.8
GEMEncoder=ViT-B/16, Model=CLIP, Pretraining=WIT-400M, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=false2023.1246.2
CLIP SurgeryEncoder=ViT-B/16, Model=CLIP, Pretraining=WIT-400M, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=false, Evaluation_Source=Current Paper2023.1241.2
ViL-SegEncoder=ViT-B/16, Model=scratch, Pretraining=GCC, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=true, Relaxed Constraints=true2023.1234.4
MaskCLIPEncoder=ViT-B/16, Model=CLIP, Pretraining=WIT-400M, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=false, Evaluation_Source=Current Paper2023.1228.6
ZS3NetEncoder=ResNet101, Model=scratch, Pretraining=VOC, Context, Annotation=SM, Localization Annotation=true, Localization Fine-tuning=true, Relaxed Constraints=true2023.1217.7
SPNetEncoder=ResNet101, Model=scratch, Pretraining=COCO, VOC, Context, Annotation=SM, Localization Annotation=true, Localization Fine-tuning=true, Relaxed Constraints=true2023.1215.6
CLIPEncoder=ViT-B/16, Model=CLIP, Pretraining=WIT-400M, Annotation=IT, Localization Annotation=false, Localization Fine-tuning=false2023.1210.4