List your company
ResearchFormerly WizWand

Semantic Segmentation on Pascal Context 459

42.4mIoUSELF1E-2B
3.413.52523.6533.775Oct 9, 2022May 6, 2023Dec 2, 2023Jun 28, 2024Jan 24, 2025Aug 21, 2025Mar 19, 2026
Updated 7mo ago

Evaluation results

MethodLinks
SELF1E-2Btrained on corresponding datasets=true2026.0342.4
PCA-SegBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0326.7
CAT-Seg+DeCLIPBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0525.9
DeCLIPBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0325.9
LSMSegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1125.6
LLMFormerBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0325.4
H-CLIPBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0324.2
CAT-SegBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0523.8
CAT-SegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1123.8
CAT-SegBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0323.8
DPSegVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2024.1123.5
MaskAdapterVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2024.1122.7
Mask-AdapterBackbone=ConvNeXt-L, Training Dataset=COCO-Stuff2026.0322.7
SEDVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2024.1122.6
SEDBackbone=ConvNeXt-L, Training Dataset=COCO-Stuff2026.0322.6
PCA-SegBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.0322.3
MAFT+VLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1121.6
CAT-Seg+DeCLIPBackbone=ViT-B/16, Training Set=COCO-Stuff2025.0521.4
DeCLIPBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.0321.4
EBSegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1121
EBSegBackbone=ViT-L/14, Training Dataset=COCO-Stuff2026.0321
LSMSegVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1120.3
FrozenSegBackbone=ConvNeXt-L, Training Set=COCO-Panoptic2025.0519.7
H-CLIPBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.0319.4
CAT-SegBackbone=ViT-B/16, Training Set=COCO-Stuff2025.0519
CAT-SegVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1119
CAT-SegBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.0319
SELF1E-2B*zero-shot=true, trained on corresponding datasets=false2026.0318.9
SEDVLM=ConvNeXt-B, Training Dataset=COCO-Stuff2024.1118.6
SEDBackbone=ConvNeXt-B, Training Dataset=COCO-Stuff2026.0318.6
FC-CLIPBackbone=ConvNeXt-L, Training Set=COCO-Panoptic2025.0518.2
FC-CLIPVLM=ConvNeXt-L, Training Dataset=COCO Panoptic2024.1118.2
Mask-AdapterBackbone=ConvNeXt-B, Training Dataset=COCO-Stuff2026.0317.9
MaskFormerbackbone=R-101c, training dataset=Same as test2022.1017.4
EBSegVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1117.3
EBSegBackbone=ViT-B/16, Training Dataset=COCO-Stuff2026.0317.3
SANBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0517.1
MAFTBackbone=ConvNeXt-L, Training Set=COCO-Stuff2025.0517
SCANVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1116.7
SANVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1115.7
ODISETraining Dataset=COCO, Supervision: label=true, Supervision: mask=true, Supervision: caption=false2023.0314.5
ODISEBackbone=ViT-L/14, Training Set=COCO-Panoptic2025.0514.5
ODISEVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1114.5
ODISEBackbone=ViT-L/14, Training Dataset=COCO-Panoptic2026.0314.5
ODISETraining Dataset=COCO, Supervision: label=false, Supervision: mask=false, Supervision: caption=true2023.0313.8
ODISEBackbone=UNet+M2F, Training data=LAION+CLIP+COCO2023.0613.8
SCANVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1113.2
SANVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1112.6
OVSegbackbone=Swin-B, training dataset=COCO-Stuff-1712022.1012.4
OVSegBackbone=Swin-B, Training data=COCO stuff+cap2023.0612.4
OVSegBackbone=ViT-L/14, Training Set=COCO-Stuff2025.0512.4
OVSegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1112.4
OVSegBackbone=ViT-L/14, Training Dataset=COCO-Stuff + Caption2026.0312.4
DaTaSegBackbone=ViTDet-B, Training data=COCO panoptic + ADE semantic2023.0611.6
OpenSegBackbone=Eff-b7, Training data=COCO+Loc. Narr.2023.0611.5
OpenSegVLM=ALIGN EN-B7, Training Dataset=COCO Panoptic2024.1111.5
DaTaSegBackbone=R-50, Training data=COCO panoptic2023.0611.1
DaTaSegBackbone=ViTDet-L, Training data=COCO panoptic + ADE semantic + O365 bbox2023.0611.1
OVSegbackbone=R-101c, training dataset=COCO-Stuff-1712022.1011
OVSegBackbone=R-101c, Training data=COCO stuff+cap2023.0611
OVSegVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1111
OVSegBackbone=ViT-B/16, Training Dataset=COCO-Stuff + Caption2026.0311
OVSegbackbone=R-101c, training dataset=COCO-Stuff-1562022.1010.4
ZegFormer+Backbone=ViT-B/16, Training Set=COCO-Stuff2025.0510.4
ZegFormerVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff2024.1110.4
SimSegVLM=CLIP ViT-L/14, Training Dataset=COCO-Stuff2024.1110.2
PSALM2026.0310.2
MaskCLIPTraining Dataset=COCO, Supervision: label=true, Supervision: mask=false, Supervision: caption=false2023.0310
MaskCLIPBackbone=R-50, Training data=COCO pan+CLIP2023.0610
DeOPVLM=CLIP ViT-B/16, Training Dataset=COCO-Stuff-1562024.119.4
ZegFormerBackbone=ViT-B/16, Training Dataset=COCO-Stuff-1562026.039.1
OpenSegbackbone=Eff-B7, training dataset=COCO Panoptic2022.109
OpenSegTraining Dataset=COCO, Supervision: label=false, Supervision: mask=false, Supervision: caption=true2023.039
OpenSegBackbone=R-101, Training data=COCO pan+cap2023.069
LSeg+backbone=Eff-B7, training dataset=COCO Panoptic2022.107.8
LSeg+Training Dataset=COCO, Supervision: label=true, Supervision: mask=true, Supervision: caption=false2023.037.8
Lseg+VLM=ALIGN EN-B7, Training Dataset=COCO-Stuff2024.117.8
GKCBackbone=ViT-B/16, Training Dataset=COCO Panoptic2026.037.1
OpenSegbackbone=R-101, training dataset=COCO Panoptic2022.106.5
LSeg+backbone=R-101, training dataset=COCO Panoptic2022.105.2
LSeg+Backbone=ALIGN, Training Dataset=COCO-Stuff2026.035.2
GroupViTTraining Dataset=GCC+YFCC, Supervision: label=false, Supervision: mask=false, Supervision: caption=true2023.034.9