List your company
ResearchFormerly WizWand

Semantic Segmentation on PASCAL VOC Original (Full) 2012 (train)

90.8mIoUUniMatch V2
72.49677.2488286.752Mar 2, 2023Jun 8, 2023Sep 15, 2023Dec 23, 2023Mar 30, 2024Jul 7, 2024Oct 14, 2024
Updated 8mo ago

Evaluation results

MethodLinks
UniMatch V2Encoder=DINOv2-B, #Params=97.5M2024.1090.8
Labeled Only (86.5)Encoder=DINOv2-B2024.1088.3
UniMatch V2Encoder=DINOv2-S, #Params=24.8M2024.1087.8
SemiVLVenue=ECCV’24, Encoder=CLIP-B, #Params=88.0M2024.1087.3
Labeled Only (85.0)Encoder=DINOv2-S2024.1085.6
UniMatch V1Venue=CVPR’23, Encoder=CLIP-B, #Params=88.0M2024.1084
AllSparkVenue=CVPR’24, Encoder=MiT-B5, #Params=89.3M2024.1082.1
Diverse CoTVenue=ICCV’23, Encoder=RN-101, #Params=59.5M2024.1082
DDFPVenue=CVPR’24, Encoder=RN-101, #Params=59.5M2024.1082
ESLVenue=ICCV’23, Encoder=RN-101, #Params=59.5M2024.1081.8
CorrMatchVenue=CVPR’24, Encoder=RN-101, #Params=59.5M2024.1081.8
BeyondPixelsVenue=ECCV’24, Encoder=RN-101, #Params=59.5M2024.1081.7
DAWVenue=NeurIPS’23, Encoder=RN-101, #Params=59.5M2024.1081.5
AugSegVenue=CVPR’23, Encoder=RN-101, #Params=59.5M2024.1081.4
iMASVenue=CVPR’23, Encoder=RN-101, #Params=59.5M2024.1081.2
UniMatch V1Venue=CVPR’23, Encoder=RN-101, #Params=59.5M2024.1081.2
PCRVenue=NeurIPS’22, Encoder=RN-101, #Params=59.5M2024.1080.7
CCVCBackbone=ResNet-101, Crop Size=512, Training Epochs=402023.0380.5
GTA-SegVenue=NeurIPS’22, Encoder=RN-101, #Params=59.5M2024.1080.5
PS-MTBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0380
PS-MTVenue=CVPR’22, Encoder=RN-101, #Params=59.5M2024.1080
U2PLBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0379.5
U2PLVenue=CVPR’22, Encoder=RN-101, #Params=59.5M2024.1079.5
ST++Backbone=ResNet-101, Crop Size=512, Training Epochs=802023.0379.1
ST++Venue=CVPR’22, Encoder=RN-101, #Params=59.5M2024.1079.1
CutMix-SegBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0376.5
PC2SegBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0374.2
Supervised BaselineBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0373.5
Labeled OnlyEncoder=RN-101, #Params=59.5M2024.1073.5
PseudoSegBackbone=ResNet-101, Crop Size=512, Training Epochs=802023.0373.2