List your company
ResearchFormerly WizWand

Open-vocabulary Semantic Segmentation on ADE20K 150 (test)

35.2mIoUSED
9.61616.25822.929.542Nov 27, 2023
Updated 8mo ago

Evaluation results

MethodLinks
SEDVLM=ConvNeXt-L, Training dataset=COCO-Stuff2023.1135.2
FC-CLIPVLM=ConvNeXt-L, Training dataset=COCO Panoptic [26]2023.1134.1
SANVLM=ViT-L/14, Training dataset=COCO-Stuff2023.1133.3
SEDVLM=ConvNeXt-B, Training dataset=COCO-Stuff2023.1131.6
CAT-SegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff2023.1131.5
PACLVLM=ViT-B/16, Training dataset=GCC [40]+YFCC [44]2023.1131.4
ODISEVLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.1129.9
OVSegVLM=ViT-L/14, Feature backbone=Swin-B, Training dataset=COCO-Stuff+COCO Caption2023.1129.6
HIPIEVLM=BERT-B [12], Feature backbone=ViT-H, Training dataset=COCO Panoptic [26]2023.1129
SANVLM=ViT-B/16, Training dataset=COCO-Stuff2023.1127.5
CAT-SegVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1127.2
OpenSegVLM=ALIGN, Feature backbone=Eff-B7 [43], Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.1126.4
OVSegVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff+COCO Caption2023.1124.8
Ding et al.VLM=ViT-L/14, Training dataset=COCO Panoptic [26]2023.1123.7
DeOPVLM=ViT-B/16, Feature backbone=ResNet-101c, Training dataset=COCO-Stuff-1562023.1122.9
SimBaselineVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1120.5
Han et al.VLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]2023.1118.8
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1118
OpenSegVLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO Panoptic [26]+Loc. Narr. [36]2023.1117.5
ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training dataset=COCO-Stuff-1562023.1116.9
LSeg+VLM=ALIGN, Feature backbone=ResNet-101, Training dataset=COCO-Stuff2023.1113
GroupViTVLM=ViT-S/16, Training dataset=GCC [40]+YFCC [44]2023.1110.6