List your company
ResearchFormerly WizWand

Multi-label Classification on PASCAL VOC 2007/2012 (test)

95.48Macro AUCCentralized
83.249686.424889.692.7752Sep 16, 2025
Updated 7mo ago

Evaluation results

MethodLinks
CentralizedBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Optimizer=AdamW, Batch Size=322025.0995.4874.6196.1176.94
CentralizedBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Optimizer=AdamW2025.0995.4874.6196.1176.94
FedNCA-MLBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Initial Learning Rate=1 x 10^-4, Weight Decay=0.01, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.8264.2894.5267.61
FedProxBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.5557.0494.0464.43
FedAvgBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Initial Learning Rate=1 x 10^-4, Weight Decay=0.01, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.5457.5794.1364.67
FedCurvBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.5357.3694.164.6
SCAFFOLDBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.4149.6493.661.44
FedAvgBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Initial Learning Rate=1 x 10^-4, Weight Decay=0.01, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.3147.7393.0560.46
SCAFFOLDBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.1757.4494.0364.95
FedProxBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.1449.4993.862.18
FedCurvBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.1348.5493.8160.49
FedNCA-MLBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Initial Learning Rate=1 x 10^-4, Weight Decay=0.01, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0993.0161.0893.765.05
FedLGTBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0991.9362.1191.7567.58
FedLGTBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0991.2556.5391.4663.51
SphereFedBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0984.2532.4485.9435.18
SphereFedBackbone=ResNet-18, Pre-training=ImageNet-pretrained weights, Communication Rounds=100, Local Epochs per round=1, Batch Size=32, Optimizer=AdamW, Negative feature rejection coefficient (lambda_1)=0.01, Positive feature contrastive coefficient (lambda_2)=12025.0983.7233.4984.3838.19