List your company
ResearchFormerly WizWand

Open-vocabulary Semantic Segmentation on ADE20K-847 (test)

14.8mIoUFC-CLIP
2.0085.3298.6511.971Nov 27, 2023
Updated 8mo ago

Evaluation results

MethodLinks
FC-CLIPVLM=ConvNeXt-L, Training dataset=COCO Panoptic [26]2023.1114.8
SEDVLM=ConvNeXt-L, Training dataset=COCO-Stuff2023.1113.9
SANVLM=ViT-L/14, Training dataset=COCO-Stuff2023.1113.7
SEDVLM=ConvNeXt-B, Training dataset=COCO-Stuff2023.1111.4
ODISEVLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.1111.1
CAT-SegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff2023.1110.8
SANVLM=ViT-B/16, Training dataset=COCO-Stuff2023.1110.1
OVSegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff+COCO Caption2023.119
CAT-SegVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.118.4
Ding et al.VLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.118.2
OpenSegVLM=ALIGN, Feature backbone=Eff-B7 [43], Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.118.1
DeOPVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff-1562023.117.1
OVSegVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff+COCO Caption2023.117.1
SimBaselineVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.117
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.115.6
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff-1562023.114.9
OpenSegVLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.114.4
GroupViTVLM=ViT-S/16, Training dataset=GCC [40]+YFCC [44]2023.114.3
Han et al.VLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]2023.113.5
LSeg+VLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.112.5