List your company
ResearchFormerly WizWand

Semantic Segmentation on PAS-20

97.3mIoUDCP-CLIP
15.1436.4757.879.13Dec 16, 2024Mar 1, 2025May 16, 2025Jul 30, 2025Oct 14, 2025Dec 28, 2025Mar 14, 2026
Updated 7mo ago

Evaluation results

MethodLinks
DCP-CLIPVLM=CLIP ViT-L/14, Training dataset=COCO-Stuff2026.0397.3
SCANCLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1297.2
SCANVLM=CLIP ViT-B/16, Additional Backbone=Swin-B, Training dataset=COCO-Stuff2026.0397.2
CAT-SegCLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1297
SCANVLM=CLIP ViT-B/16, Additional Backbone=Swin-B, Training dataset=COCO-Stuff2026.0397
MaskCLIP++ w/ MAFT+CLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1296.8
BBNVLM=CLIP ViT-L/14, Training dataset=COCO-Stuff2026.0396.8
CAT-SegVLM=CLIP ViT-L/14, Additional Backbone=Swin-B, Training dataset=COCO-Stuff2026.0396.6
MAFT+CLIP arch.=ConvNeXt-L, Training dataset=COCO Stuff2024.1296.5
MaskCLIP++ w/ FC-CLIPCLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1296.4
EBSegVLM=CLIP ViT-L/14, Additional Backbone=SAM [41], Training dataset=COCO-Stuff2026.0396.4
SEDCLIP arch.=ConvNeXt-L, Training dataset=COCO Stuff2024.1296.1
SEDVLM=ConvNeXt-L, Training dataset=COCO-Stuff2026.0396.1
DCP-CLIPVLM=CLIP ViT-B/16, Training dataset=COCO-Stuff2026.0395.9
GBAVLM=ConvNeXt-L, Training dataset=COCO Panoptic [54]2026.0395.8
SANVLM=CLIP ViT-L/14, Training dataset=COCO-Stuff2026.0395.5
FC-CLIPCLIP arch.=ConvNeXt-L, Training dataset=COCO Panoptic2024.1295.4
FC-CLIPVLM=ConvNeXt-L, Training dataset=COCO Panoptic [54]2026.0395.4
SANCLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1294.6
EBSegVLM=CLIP ViT-B/16, Additional Backbone=SAM [41], Training dataset=COCO-Stuff2026.0394.6
OVSegCLIP arch.=ViT-L/14, Training dataset=COCO Stuff2024.1294.5
OVSegVLM=CLIP ViT-L/14, Additional Backbone=Swin-B, Training dataset=COCO-Stuff+COCO Caption2026.0394.5
SEDVLM=ConvNeXt-B, Training dataset=COCO-Stuff2026.0394.4
SANVLM=CLIP ViT-B/16, Training dataset=COCO-Stuff2026.0394
CAT-SegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101, Training dataset=COCO-Stuff2026.0393.7
OVSegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101c, Training dataset=COCO-Stuff+COCO Caption2026.0392.6
CELVLM=CLIP R50, Training dataset=COCO-Stuff2026.0391.8
DeOPVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101c, Training dataset=COCO-Stuff-1562026.0391.7
ZSsegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101, Training dataset=COCO-Stuff2026.0388.4
ZegFormerVLM=CLIP ViT-B/16, Additional Backbone=ResNet-101, Training dataset=COCO-Stuff-1562026.0386.2
PACLVLM=CLIP ViT-B/16, Training dataset=GCC [50]+YFCC [51]2026.0372.3
OpenSegVLM=ALIGN, Additional Backbone=Eff-B7 [60], Training dataset=COCO Panoptic [54]+LOc. Narr. [55]2026.0372.2
LSegVLM=CLIP ViT-B/32, Additional Backbone=ViT-L/16, Training dataset=PASCAL VOC-152026.0352.3
GroupViTVLM=ViT-S/16, Training dataset=GCC [50] +YFCC [51]2026.0350.7
LSegVLM=CLIP ViT-B/32, Additional Backbone=ResNet-101, Training dataset=PASCAL VOC-152026.0347.4
ZS3NetAdditional Backbone=ResNet-101, Training dataset=PASCAL VOC2026.0338.3
SPNetAdditional Backbone=ResNet-101, Training dataset=PASCAL VOC2026.0318.3