List your company
ResearchFormerly WizWand

Human Part Segmentation on PASCAL-Context (test)

61.93mIoUSingle Task
36.34642.98849.6356.272Nov 22, 2023Dec 13, 2023Jan 3, 2024Jan 25, 2024Feb 15, 2024Mar 7, 2024Mar 29, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Single TaskBackbone=Swin-Tiny, Trainable Parameters (M)=112.62, Single Inference For All Tasks=false2024.0361.93—
HyperFormerBackbone=Swin-Tiny, Trainable Parameters (M)=72.77, Single Inference For All Tasks=false2024.0360.73—
MTL - Full Fine TuningBackbone=Swin-Tiny, Trainable Parameters (M)=30.06, Single Inference For All Tasks=true2024.0360.24—
MTLORABackbone=Swin-Tiny, Rank (r)=64, Trainable Parameters (M)=8.34, Single Inference For All Tasks=true2024.0359.84—
MTLORABackbone=Swin-Tiny, Rank (r)=32, Trainable Parameters (M)=6.08, Single Inference For All Tasks=true2024.0359.46—
VL-AdapterBackbone=Swin-Tiny, Trainable Parameters (M)=4.74, Single Inference For All Tasks=false2024.0359.15—
PolyhistorBackbone=Swin-Tiny, Trainable Parameters (M)=8.96, Single Inference For All Tasks=false2024.0359.15—
MTLORABackbone=Swin-Tiny, Rank (r)=16, Trainable Parameters (M)=4.95, Single Inference For All Tasks=true2024.0358.99—
MTLORA+Backbone=Swin-Tiny, Rank (r)=16, Trainable Parameters (M)=4.29, Single Inference For All Tasks=true2024.0358.7—
MTLORA+Backbone=Swin-Tiny, Rank (r)=8, Trainable Parameters (M)=3.15, Single Inference For All Tasks=true2024.0358.3—
MTLORA+Backbone=Swin-Tiny, Rank (r)=4, Trainable Parameters (M)=2.57, Single Inference For All Tasks=true2024.0357.77—
LoRABackbone=Swin-Tiny, Trainable Parameters (M)=2.87, Single Inference For All Tasks=false2024.0357.73—
AdapterBackbone=Swin-Tiny, Trainable Parameters (M)=11.24, Single Inference For All Tasks=false2024.0357.38—
CompactorBackbone=Swin-Tiny, Trainable Parameters (M)=2.78, Single Inference For All Tasks=false2024.0356.41—
BitfitBackbone=Swin-Tiny, Trainable Parameters (M)=2.85, Single Inference For All Tasks=false2024.0355.99—
Compactor++Backbone=Swin-Tiny, Trainable Parameters (M)=2.66, Single Inference For All Tasks=false2024.0355.69—
LocalClient Setup=Multi-Task2023.1155.010
FEDHCA2Client Setup=Multi-Task2023.1155.010.75
MaT-FLClient Setup=Multi-Task2023.1154.78-0.16
FedPerClient Setup=Multi-Task2023.1154.75-0.16
FedAMPClient Setup=Multi-Task2023.1154.10.27
MTL - Tuning Decoders OnlyBackbone=Swin-Tiny, Trainable Parameters (M)=1.94, Single Inference For All Tasks=true2024.0353.48—
FedAvgClient Setup=Multi-Task2023.1152.88-7.56
VPT-deepBackbone=Swin-Tiny, Trainable Parameters (M)=3.43, Single Inference For All Tasks=false2024.0352.54—
FEDHCA^2Backbone=Swin-T, Client Setup=Single-Task2023.1152.3—
VPT-shallowBackbone=Swin-Tiny, Trainable Parameters (M)=2.57, Single Inference For All Tasks=false2024.0352.27—
FedAMPBackbone=Swin-T, Client Setup=Single-Task2023.1152.05—
DittoClient Setup=Multi-Task2023.1151.45-4.67
FedProxClient Setup=Multi-Task2023.1150.78-8.12
LocalBackbone=Swin-T, Client Setup=Single-Task2023.1149.94—
MaT-FLBackbone=Swin-T, Client Setup=Single-Task2023.1148.63—
FedPerBackbone=Swin-T, Client Setup=Single-Task2023.1146.56—
DittoBackbone=Swin-T, Client Setup=Single-Task2023.1139.69—
FedProxBackbone=Swin-T, Client Setup=Single-Task2023.1138.1—
FedAvgBackbone=Swin-T, Client Setup=Single-Task2023.1137.33—