List your company
ResearchFormerly WizWand

Semantic Segmentation on Cross-Domain Average (Cityscapes, BDD100K, Mapillary)

67.46mIoULoCA‡
29.364839.254949.14559.0351Oct 22, 2024Feb 3, 2025May 18, 2025Aug 30, 2025Dec 12, 2025Mar 26, 2026Jul 8, 2026
Updated 3mo ago

Evaluation results

MethodLinks
LoCA‡Backbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=5.0M, GFLOPs=152, Pre-trained=DINO2026.0767.46—
LoCABackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=5.0M, GFLOPs=152, Pre-trained=DINO2026.0766.49—
SoMABackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=4.3M, GFLOPs=152, Pre-trained=DINO2026.0766.13—
LoRA (Linear)Backbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=4.3M, GFLOPs=152, Pre-trained=DINO2026.0765.29—
LoRABackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=25.9M, GFLOPs=152, Pre-trained=DINO2026.0764.95—
FSFBackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=0.8M, GFLOPs=152, Pre-trained=DINO2026.0764.02—
FFTBackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=196.2M, GFLOPs=152, Pre-trained=DINO2026.0763.87—
SoMABackbone=ViT-B, Param.=86.5M, Trainable Param.=2.3M, GFLOPs=216, Pre-trained=DINO2026.0763.84—
LoCABackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=3.4M, GFLOPs=81, Pre-trained=DINO2026.0763.76—
CoLoRABackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=3.6M, GFLOPs=152, Pre-trained=DINO2026.0763.59—
LoCA‡Backbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=3.4M, GFLOPs=81, Pre-trained=DINO2026.0763.32—
CABackbone=ConvNeXt-L, Param.=196.2M, Trainable Param.=4.5M, GFLOPs=152, Pre-trained=DINO2026.0762.96—
SoMABackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=2.9M, GFLOPs=81, Pre-trained=DINO2026.0762.77—
LoRA (Linear)Backbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=2.9M, GFLOPs=81, Pre-trained=DINO2026.0762.43—
LoRABackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=17.2M, GFLOPs=81, Pre-trained=DINO2026.0762.3—
FFTBackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=87.56M, GFLOPs=81, Pre-trained=DINO2026.0761.4—
CoLoRABackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=2.2M, GFLOPs=81, Pre-trained=DINO2026.0760.53—
FSFBackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=0.6M, GFLOPs=81, Pre-trained=DINO2026.0760.27—
CABackbone=ConvNeXt-B, Param.=87.56M, Trainable Param.=2.3M, GFLOPs=81, Pre-trained=DINO2026.0759.96—
FFTBackbone=ViT-B, Param.=86.5M, Trainable Param.=86.5M, GFLOPs=216, Pre-trained=DINO2026.0758.65—
LoCABackbone=MambaVision-L3, Param.=737.5M, Trainable Param.=9.0M, GFLOPs=1,556, Pre-trained=ImageNet21k2026.0757.31—
FFTBackbone=MambaVision-L3, Param.=737.5M, Trainable Param.=737.5M, GFLOPs=1,556, Pre-trained=ImageNet21k2026.0751.61—
LoCABackbone=ResNet101, Param.=42.3M, Trainable Param.=2.8M, GFLOPs=42, Pre-trained=ImageNet21k2026.0746.72—
SoMA†Backbone=ResNet101, Param.=42.3M, Trainable Param.=2.5M, GFLOPs=42, Pre-trained=ImageNet21k2026.0745.5—
FFTBackbone=ResNet101, Param.=42.3M, Trainable Param.=42.3M, GFLOPs=42, Pre-trained=ImageNet21k2026.0744.79—
LoCABackbone=MambaVision-B, Param.=96.7M, Trainable Param.=2.5M, GFLOPs=211, Pre-trained=ImageNet21k2026.0744.2—
PinMemBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Re-evaluated2024.1038.7447.43
LFMEBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Re-evaluated2024.1038.3749.62
RobustNetBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Cited from [19]2024.1036.76—
IBN-NetBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Cited from [19]2024.1035.27—
FFTBackbone=MambaVision-B, Param.=96.7M, Trainable Param.=96.7M, GFLOPs=211, Pre-trained=ImageNet21k2026.0732.52—
BaselineBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Re-evaluated2024.1032.3845.56
SDBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Re-evaluated2024.1031.3945.05
BaselineBackbone=ResNet-50, Source Datasets=GTAV + Synthia, Implementation Source=Cited from [19]2024.1030.83—