List your company
ResearchFormerly WizWand

Semantic Segmentation on PASCAL-Context 59 classes (test)

62.3mIoUDPSeg
16.33228.26640.252.134Jun 2, 2016Nov 29, 2017May 28, 2019Nov 23, 2020May 22, 2022Nov 18, 2023May 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DPSegVLM=ConvNeXt-L, Inference Mode=II, Training Dataset=COCO-Stuff2025.0562.3
CAT-SegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0562
DPSegVLM=ConvNeXt-L, Inference Mode=I, Training Dataset=COCO-Stuff2025.0562
SEDVLM=ConvNeXt-L, Training Dataset=COCO-Stuff2025.0560.6
DPT-Hybrid#params.=124.0M, FLOPs=1231.5G, Multi-scale testing=true, Extra pre-training on ADE20K=true2021.1060.5
SANVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0560.2
EBSegVLM=ViT-L/14, Training Dataset=COCO-Stuff2025.0560.2
HIPIEVLM=BERT-B, Backbone=ViT-H, Training Dataset=COCO Panoptic [20]2025.0559.3
SCANVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0559.3
HRFormer-B + OCR#params.=56.2M, FLOPs=1119.9G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1058.5
SCANVLM=ViT-B/16, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0558.4
DPSegVLM=ConvNeXt-B, Inference Mode=II, Training Dataset=COCO-Stuff2025.0558.4
FC-CLIPVLM=ConvNeXt-L, Training Dataset=COCO Panoptic [20]2025.0558.4
DPSegVLM=ConvNeXt-B, Inference Mode=I, Training Dataset=COCO-Stuff2025.0558.1
USE+SAMVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff2025.0557.8
CAT-SegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0557.5
SEDVLM=ConvNeXt-B, Training Dataset=COCO-Stuff2025.0557.3
ODISEVLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.0557.3
EBSegVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0556.7
HRNet-W48 + OCR#params.=74.5M, FLOPs=924.7G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1056.2
SETR-MLA#params.=309.5M, FLOPs=2138.6G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1055.8
OVSegVLM=ViT-L/14, Backbone=Swin-B, Training Dataset=COCO-Stuff+COCO Caption2025.0555.7
SETR-PUP#params.=317.8M, FLOPs=2326.7G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1055.3
GFFNetBackbone=ResNet-1012019.0454.2
Deeplabv3#params.=87.1M, FLOPs=1394.0G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1054.1
PSPNet#params.=68.0M, FLOPs=1028.8G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.1054
SANVLM=ViT-B/16, Training Dataset=COCO-Stuff2025.0553.8
BFPBackbone=ResNet-101, UAGS=true, Boundary aware=true, multi-scale testing=true2019.0853.6
OVSegVLM=ViT-B/16, Backbone=ResNet-101c, Training Dataset=COCO-Stuff+COCO Caption2025.0553.3
SVCNetBackbone=ResNet-1012019.0453.2
DANetBackbone=ResNet-1012019.0452.6
EncNet2019.0851.7
EncNetBackbone=ResNet-1012019.0451.7
CCL+GMA2019.0851.6
CCLNetBackbone=ResNet-1012019.0451.6
GFFNetBackbone=ResNet-502019.0451
MSCI2019.0850.3
DANetBackbone=ResNet-502019.0450.1
PACLVLM=ViT-B/16, Training Dataset=GCC [41] + YFCC[45]2025.0550.1
EncNetBackbone=ResNet-502019.0449
PSPNetBackbone=ResNet-1012019.0447.8
SimSegVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0547.7
RefineNet2019.0847.3
Ding et al.VLM=ViT-L/14, Training Dataset=COCO Panoptic [20]2025.0545.9
DeepLabMSC=true, COCO=true, Aug=true, ASPP=true, CRF=true, Backbone=ResNet-1012016.0645.7
DeepLab-v2+CRF2019.0845.7
ZegFormerVLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0545.5
Han et al.VLM=ViT-B/16, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20]2025.0545.2
EFCN2019.0845
OpenSegVLM=ALIGN, Backbone=Eff-B7 [44], Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.0544.8
DeepLabMSC=true, COCO=true, Aug=true, ASPP=true, Backbone=ResNet-1012016.0644.7
VeryDeep2016.0644.5
DAG-RNN2019.0843.7
DeepLabMSC=true, COCO=true, Aug=true, Backbone=ResNet-1012016.0643.5
Context2016.0643.3
DeepLabMSC=true, COCO=true, Backbone=ResNet-1012016.0642.9
DeepLabMSC=true, Backbone=ResNet-1012016.0641.4
PixelNet2019.0841.4
HO_CRF2016.0641.3
HO-CRF2019.0841.3
BoxSup2016.0640.5
BoxSup2019.0840.5
ParseNet2016.0640.4
OpenSegVLM=ALIGN, Backbone=ResNet-101, Training Dataset=COCO Panoptic [20] + Loc. Narr. [36]2025.0540.1
DeepLabLargeFOV=true, CRF=true, Backbone=VGG-162016.0639.6
DeepLab (ResNet-101)Backbone=ResNet-1012016.0639.6
CRF-RNN2016.0639.3
FCN-8s2019.0839.1
ZS3NetBackbone=ResNet-101, Training Dataset=PASCAL VOC2025.0538.3
FCN-8s2016.0637.8
DeepLab (VGG-16)LargeFOV=true, Backbone=VGG-162016.0637.6
LSeg+VLM=ALIGN RN-101, Backbone=ResNet-101, Training Dataset=COCO-Stuff2025.0536
CFM2016.0634.4
O2P2016.0618.1
O2P2019.0818.1