List your company
ResearchFormerly WizWand

Semantic Segmentation on Cityscapes (Semseg mIoU)

93.95mIoUB^3-Net
73.586878.873484.1689.4466Aug 22, 2024Dec 13, 2024Apr 6, 2025Jul 29, 2025Nov 20, 2025Mar 14, 2026Jul 6, 2026
Updated 3mo ago

Evaluation results

MethodLinks
B^3-Net2026.0593.95
BridgeNet2026.0593.72
MTMamba++2026.0591.11
MTMamba2026.0590.77
InvPT2026.0589.86
MTAN2026.0588.9
PAD-Net2026.0585.59
TaskPrompter2026.0585.26
SwinMTL2026.0585.04
Lorentz (SegFormer-B3)Backbone=B32026.0483.7
EoMTBackbone=ViT-Large, FPS A100=17.6, FPS Orin=3.6, GFLOPs=1721.3, Resolution=1024 × 10242026.0583.6
SCASegBackbone=MiT-B5, Params. (M)=92.4, GFLOPs=1173.02024.1183.5
NaLaFormer-SPARA=25M, F=206G2025.0683.5
SCASegBackbone=MiT-B4, Params. (M)=71.8, GFLOPs=953.02024.1183.2
ContrastiveSegYear=2021, Backbone=OCR2024.1183.2
U-MixFormerYear=2025, Backbone=MiT-B5, Params. (M)=93.0, GFLOPs=1171.02024.1183.1
SCASegBackbone=MSCAN-B, Params. (M)=36.5, GFLOPs=261.02024.1183
SCASegBackbone=MiT-B3, Params. (M)=55.1, GFLOPs=675.02024.1183
TokenMaskBackbone=ViT-Large, FPS A100=21.9, FPS Orin=4.2, GFLOPs=1251.6, Resolution=1024 × 10242026.0582.9
VWFormerYear=2024, Backbone=MiT-B5, Params. (M)=84.6, GFLOPs=1213.02024.1182.8
MetaSegYear=2024, Backbone=MSCAN-B, Params. (M)=29.6, GFLOPs=251.12024.1182.7
VWFormerYear=2024, Backbone=MiT-B4, Params. (M)=64.0, GFLOPs=993.02024.1182.7
FeedFormerYear=2023, Backbone=MiT-B5, Params. (M)=85.6, GFLOPs=1180.02024.1182.7
SegNeXtYear=2022, Backbone=MSCAN-B, Params. (M)=27.6, GFLOPs=275.72024.1182.6
FeedFormerYear=2023, Backbone=MiT-B4, Params. (M)=65.0, GFLOPs=960.02024.1182.6
MetaSegYear=2024, Backbone=MiT-B5, Params. (M)=85.0, GFLOPs=1143.02024.1182.5
NaLaFormer-TPARA=14M, F=111G2025.0682.5
VWFormerYear=2024, Backbone=MiT-B3, Params. (M)=47.3, GFLOPs=715.02024.1182.4
SegFormerYear=2021, Backbone=MiT-B5, Params. (M)=84.7, GFLOPs=1460.42024.1182.4
SegFormer (B4)Backbone=B42026.0482.3
VWFormerYear=2024, Backbone=MSCAN-B, Params. (M)=28.3, GFLOPs=302.02024.1182.3
M2H-MX-L2026.0382.28
M2H-MX-L2026.0582.28
SETRYear=2021, Backbone=ViT-Large, Params. (M)=318.32024.1182.2
MTA-clip (ViT-B)Backbone=ViT-B2026.0482.1
FeedFormerYear=2023, Backbone=MSCAN-B, Params. (M)=30.5, GFLOPs=269.02024.1182.1
MetaSegYear=2024, Backbone=MiT-B4, Params. (M)=63.6, GFLOPs=923.02024.1182.1
EfficientViT-B2PARA=15M, F=74G2025.0682.1
FeedFormerYear=2023, Backbone=MiT-B3, Params. (M)=48.3, GFLOPs=682.02024.1181.9
SegFormerYear=2021, Backbone=MiT-B4, Params. (M)=64.1, GFLOPs=1240.62024.1181.9
MetaSegYear=2024, Backbone=MiT-B3, Params. (M)=47.7, GFLOPs=645.02024.1181.8
EoMTBackbone=ViT-Base, FPS A100=37.5, FPS Orin=9.6, GFLOPs=628.1, Resolution=1024 × 10242026.0581.8
SegFormer (B3)Backbone=B32026.0481.7
SegFormerYear=2021, Backbone=MiT-B3, Params. (M)=47.3, GFLOPs=962.92024.1181.7
VWFormer-B2PARA=27M, F=415G2025.0681.7
ContrastiveSegYear=2021, Backbone=HRNetV2-W482024.1181.4
SegNeXt-SPARA=15M, F=125G2025.0681.3
DINOv3Number of Parameters=7B, Patch Size=16, Evaluation Protocol=Linear probing on frozen features, Evaluation Resolution=default2026.0781.1
DenseClip (R101)Backbone=R1012026.0481
EoMTBackbone=ViT-Small, FPS A100=78.3, FPS Orin=22.6, GFLOPs=165.4, Resolution=1024 × 10242026.0581
SegFormer-B2PARA=28M, F=711G2025.0681
Lorentz (DeepLab-R101)Backbone=R1012026.0480.6
TokenMaskBackbone=ViT-Base, FPS A100=51.4, FPS Orin=11.9, GFLOPs=356.6, Resolution=1024 × 10242026.0580.4
VWFormer-B1PARA=14M2025.0680.4
SupervisedAnnotation=Fine, Architecture=DeepLabV3+ (ResNet-101)2026.0480.2
DeepLabV32026.0480.1
TokenMaskBackbone=ViT-Small, FPS A100=104.4, FPS Orin=27.2, GFLOPs=90.4, Resolution=1024 × 10242026.0579.7
LingBot-Vision ViT-gNumber of Parameters=1B, Patch Size=16, Evaluation Protocol=Linear probing on frozen features, Evaluation Resolution=default2026.0779.6
DINOv3 ViT-H+Number of Parameters=0.8B, Patch Size=16, Evaluation Protocol=Linear probing on frozen features, Evaluation Resolution=default2026.0779.5
MTMamba++2026.0379.13
MTMamba++2026.0579.13
SegmenterBackbone=ViT-Large, FPS A100=20.8, FPS Orin=3.4, GFLOPs=2248.3, Resolution=1024 × 10242026.0579.1
SegFormer-B1PARA=14M, F=244G2025.0678.5
AM-RADIOv2.5Number of Parameters=1B, Patch Size=14, Evaluation Protocol=Linear probing on frozen features, Evaluation Resolution=default2026.0778.4
CTSBackbone=ViT-B/16, FPS (B=32)=80, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=true2026.0478.11
TeacherBackbone=ResNet-101, Segmentation Framework=DeepLabV32024.1178.07
MTMamba2026.0378
MTMamba2026.0578
Mask2Former-R50GFLOPs=527.4, Params (M)=44.0, FPS=2.42026.0477.5
ViT-B/16Backbone=ViT-B/16, GFLOPs=348, FPS (B=32)=44, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0477.3
ToMeBackbone=ViT-B/16, GFLOPs=∼298, FPS (B=32)=46, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0477.3
DHKDTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1177.13
DISTTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1177.1
SegmenterBackbone=ViT-Base, FPS A100=6.8, FPS Orin=9.9, GFLOPs=776.0, Resolution=1024 × 10242026.0577.1
ALGMBackbone=ViT-S/16, GFLOPs=79, FPS (B=32)=132, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=true2026.0476.9
CTSBackbone=ViT-S/16, FPS (B=32)=169, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=true2026.0476.6
SegmenterBackbone=ViT-Small, FPS A100=15.7, FPS Orin=22.1, GFLOPs=285.0, Resolution=1024 × 10242026.0576.6
ALGMBackbone=ViT-B/16, GFLOPs=∼ 211, FPS (B=32)=62, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=true2026.0476.4
CIRKDTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1176.38
ViT-S/16Backbone=ViT-S/16, GFLOPs=116, FPS (B=32)=106, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0476.3
ToMeBackbone=ViT-S/16, GFLOPs=∼97, FPS (B=32)=105, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0476.3
MPM (2,5)Backbone=ViT-B/16, GFLOPs=∼ 247, FPS (B=32)=65, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0476.3
SM-AdaptFormerInput size=1024 × 10242024.0876.25
SupervisedAnnotation=Fine, Architecture=SegFormer (MiT-B0)2026.0476
DINOv2Number of Parameters=1B, Patch Size=14, Evaluation Protocol=Linear probing on frozen features, Evaluation Resolution=default2026.0775.6
IFVDTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1175.59
CWDTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1175.55
AdaptFormerInput size=1024 × 10242024.0875.49
SKDTeacher Backbone=ResNet-101, Student Backbone=ResNet-18, Segmentation Framework=DeepLabV32024.1175.42
MPM (2,5)Backbone=ViT-S/16, GFLOPs=∼ 81, FPS (B=32)=158, Segmentation Head=Mask Transformer [26], Input Resolution=768x768, Precision=float32, Hardware=H100, Training/Fine-tuning Required=false2026.0475.3
FixMatch*Sampling=Explicit, Overlap size=7532026.0575.23
DenseFixMatchSampling=Implicit, Overlap size=7532026.0575.17
SeSAMAnnotation=Scribble, Architecture=DeepLabV3+ (ResNet-101)2026.0475.1
DenseFixMatchSampling=Explicit, Overlap size=7532026.0575.1
DenseFixMatchSampling=Implicit, # labels=14882026.0575.06
FixMatch*Sampling=Implicit, Overlap size=7532026.0575.04
FixMatch*Sampling=Implicit, # labels=14882026.0574.91
FixMatch*Sampling=Explicit, # labels=14882026.0574.91
DenseFixMatchSampling=Explicit, # labels=14882026.0574.89
DenseFixMatchSampling=Implicit, # labels=7442026.0574.37