List your company
ResearchFormerly WizWand

Open-vocabulary semantic segmentation on Pascal Context-459 (test)

22.6mIoUSED
4.1928.97113.7518.529Nov 27, 2023
Updated 8mo ago

Evaluation results

MethodLinks
SEDVLM=ConvNeXt-L, Training dataset=COCO-Stuff2023.1122.6
CAT-SegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff2023.1120.4
SEDVLM=ConvNeXt-B, Training dataset=COCO-Stuff2023.1118.6
FC-CLIPVLM=ConvNeXt-L, Training dataset=COCO Panoptic [26]2023.1118.2
SANVLM=ViT-L/14, Training dataset=COCO-Stuff2023.1117.1
CAT-SegVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1116.6
ODISEVLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.1114.5
SANVLM=ViT-B/16, Training dataset=COCO-Stuff2023.1112.6
OVSegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff+COCO Caption2023.1112.4
OpenSegVLM=ALIGN, Feature backbone=Eff-B7 [43], Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.1111.5
OVSegVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff+COCO Caption2023.1111
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1110.4
Ding et al.VLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.1110
DeOPVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff-1562023.119.4
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff-1562023.119.1
OpenSegVLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.117.9
Han et al.VLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]2023.117.1
LSeg+VLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.115.2
GroupViTVLM=ViT-S/16, Training dataset=GCC [40]+YFCC [44]2023.114.9