List your company
ResearchFormerly WizWand

Multi-label Classification on NUS-WIDE

70.1mAPQ2L
31.006441.155751.30561.4543Jul 22, 2021May 15, 2022Mar 9, 2023Dec 31, 2023Oct 24, 2024Aug 17, 2025Jun 11, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Q2LBackbone=CvT-w24, Pre-trained=ImageNet-22k2021.0770.167.676.3
ML-Decoder + AAMBackbone=TResNet-L, Input resolution=448x448, GFLOPS=36.162022.0968.3——
GAT re-weightingBackbone=TResNet-L, Input resolution=448x448, GFLOPS=35.22022.0968.1——
ML-Decoder + AAMBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=12.282022.0967.6——
ML-DecoderBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=12.28, Training strategy=our training strategy2022.0967.07——
GAT re-weightingBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=10.832022.0966.85——
Q2LBackbone=TresNetL2021.0766.36475
MlTr-1Backbone=MlTr-1, Pre-trained=ImageNet-22k2021.0766.36575.8
Q2LBackbone=TResNet-L, Input resolution=448x448, GFLOPS=60.42022.0966.3——
ML-GCNBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=10.83, Training strategy=our training strategy2022.0966.3——
Q2LBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=16.25, Training strategy=our training strategy2022.0965.79——
ASLBackbone=TresNetL2021.0765.263.675
ASLBackbone=TResNet-L, Input resolution=448x448, GFLOPS=43.52022.0965.2——
ASLBackbone=EfficientNet-V2-s, Input resolution=448x448, GFLOPS=10.83, Training strategy=our training strategy2022.0965.2——
Q2LBackbone=ResNet1012021.076563.175
Focal lossBackbone=TresNetL2021.076462.974.7
BaselineBackbone=TresNetL2021.0763.161.774.6
ICMEBackbone=ResNet1012021.0762.860.774.1
SRNBackbone=ResNet1012021.076258.573.4
MS-CMABackbone=ResNet1012021.0761.460.573.8
GATNBackbone=ResNeXt-101, Input resolution=448x448, GFLOPS=362022.0959.8——
FedMPTFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0557.1756.9471.83
Fed-MaPLeFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0553.1353.2868.65
BCPFT-FREE=true, EKE-FREE=true, OTTA=true, Backbone=ViT-B/162026.0652.78——
FedMVPFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0552.7352.6170.67
FedMPTMask=10%, Venue=Ours2026.0551.7245.1672.88
FedPGPFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0551.153.0767.72
Fed-RAMFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0550.5242.6966.79
BCPFT-FREE=true, EKE-FREE=true, OTTA=true, Backbone=ResNet-502026.0650.34——
Fed-DualCoOpFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0548.6550.3967.52
CoMCFT-FREE=false, EKE-FREE=false, OTTA=false, Backbone=ResNet-502026.0648.2——
Fed-PosCoOpFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0547.4446.0364.47
SPARCFT-FREE=true, EKE-FREE=false, OTTA=false, Backbone=ViT-B/162026.0647.3——
FedAWAFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0544.447.7864.75
Fed-TCPFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0542.944.7764.3
FedTPGFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0542.1440.3665.3
Fed-DualCoOpMask=10%, Venue=NeurIPS’222026.0540.1335.5761.16
Fed-SCPNetFramework=Federated Zero-Shot Learning, Zero-shot=true2026.0538.3541.6261.61
Fed-SCPNetMask=10%, Venue=CVPR’232026.0535.4433.2256.39
FedMPTMask=Avg, Venue=Ours2026.0532.5132.7847.86