List your company
ResearchFormerly WizWand

Semantic Segmentation on ADE20K-150 (test)

37.1mIoUDPSeg
12.03618.54325.0531.557May 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DPSegVLM=ConvNeXt-L, Inference Mode=II, Training Dataset=COCO-Stuff2025.0537.1
USE+SAMVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0537
DPSegVLM=ConvNeXt-L, Inference Mode=I, Training Dataset=COCO-Stuff2025.0536.4
SEDVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2025.0535.2
FC-CLIPVLM=ConvNeXt-L, Training Dataset=COCO Panoptic [20]2025.0534.1
SCANVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0533.5
DPSegVLM=ConvNeXt-B, Inference Mode=II, Training Dataset=COCO-Stuff2025.0533.3
SANVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0533.3
DPSegVLM=ConvNeXt-B, Inference Mode=I, Training Dataset=COCO-Stuff2025.0532.9
EBSegVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0532.8
SEDVLM=ConvNeXt-B, Training Dataset=COCO-Stuff2025.0531.6
CAT-SegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0531.5
PACLVLM=ViT-B/16, Training Dataset=GCC [41] + YFCC[45]2025.0531.4
SCANVLM=ViT-B/16, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0530.8
EBSegVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0530
ODISEVLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.0529.9
OVSegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff+COCO Caption2025.0529.6
HIPIEVLM=BERT-B, Backbone=ViT-H, Training Dataset=COCO Panoptic [20]2025.0529
SANVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0527.5
CAT-SegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0527.2
OpenSegVLM=ALIGN, Backbone=Eff-B7 [44], Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.0526.4
OVSegVLM=ViT-B/16, Backbone=ResNet-101c, Training Dataset=COCO-Stuff+COCO Caption2025.0524.8
Ding et al.VLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.0523.7
SimSegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0520.5
ZS3NetBackbone=ResNet-101, Training Dataset=PASCAL VOC2025.0519.4
Han et al.VLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20]2025.0518.8
ZegFormerVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0518
OpenSegVLM=ALIGN, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.0517.5
LSeg+VLM=ALIGN RN-101, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0513