List your company
ResearchFormerly WizWand

Image Classification on CIFAR-10-LT IF 100

89.1Top-1 AccuracyGLMC + Loss + LR
48.38458.954569.52580.0955Mar 22, 2022Nov 28, 2022Aug 7, 2023Apr 15, 2024Dec 23, 2024Sep 1, 2025May 11, 2026
Updated 3mo ago

Evaluation results

MethodLinks
GLMC + Loss + LRreweighting=Inverse-view, LR Schedule=MiLeLR2026.0589.1
GLMC + Lossreweighting=Inverse-view2026.0588.6
B-SCLVenue=NeurIPS252026.0588
GLMCVenue=CVPR232026.0587.8
ProCoBackbone=ResNet-32, Training Epochs=2002024.0385.9
GLMC + SEL2026.0585.4
FeatReconVenue=ICLR252026.0585.2
ResComBackbone=ResNet-32, Imbalanced Factor=1002022.0384.9
RBLVenue=ICML232026.0584.7
BCLBackbone=ResNet-32, Training Epochs=2002024.0384.5
Logit AdjustmentBackbone=ResNet-32, Training Epochs=2002024.0384.3
GCL + CRBackbone Net=ResNet-322023.0383.5
GCLBackbone Net=ResNet-322023.0382.7
ResLTBackbone=ResNet-32, Training Epochs=2002024.0382.4
CE* + Lossreweighting=Inverse-view2026.0582.3
MISLASBackbone=ResNet-32, Imbalanced Factor=1002022.0382.1
MISLASBackbone Net=ResNet-322023.0382.1
MiSLASVenue=CVPR212026.0582.1
CE* + Loss + LRreweighting=Inverse-view, LR Schedule=MiLeLR2026.0582
CMO + Lossreweighting=Inverse-view2026.0582
INC-DRWVenue=AISTATS232026.0581.9
De-c-TDE + CRBackbone Net=ResNet-322023.0381.8
RIDE-3 expertsVenue=ICLR212026.0581.6
CMO + Loss + LRreweighting=Inverse-view, LR Schedule=MiLeLR2026.0581.6
Balanced SoftmaxBackbone=ResNet-32, Imbalanced Factor=1002022.0381.5
FedYoYoVenue=ICCV252026.0581.5
Hybrid-PSCBackbone=ResNet-32, Imbalanced Factor=1002022.0381.4
Hybrid-SCBackbone=ResNet-32, Training Epochs=2002024.0381.4
HCLVenue=CVPR212026.0581.4
BBN + CRBackbone Net=ResNet-322023.0381.2
LDAM-DRWBackbone Net=ResNet-322023.0381
MetaSAug-LDAMBackbone=ResNet-32, Training Epochs=2002024.0380.7
Causal NormBackbone=ResNet-32, Imbalanced Factor=1002022.0380.6
Casual ModelBackbone=ResNet-32, Training Epochs=2002024.0380.6
De-c-TDEBackbone Net=ResNet-322023.0380.6
ResLTBackbone=ResNet-32, Imbalanced Factor=1002022.0380.5
BBNBackbone=ResNet-32, Imbalanced Factor=1002022.0379.9
BBNVenue=CVPR202026.0579.9
BBNBackbone=ResNet-32, Training Epochs=2002024.0379.8
BBNBackbone Net=ResNet-322023.0379.8
TSCBackbone=ResNet-32, Training Epochs=2002024.0379.7
TSCVenue=CVPR222026.0579.7
RSGBackbone=ResNet-32, Imbalanced Factor=1002022.0379.5
ETF-DR + DisA2026.0578.5
ELF+LDAMBackbone=ResNet-32, Imbalanced Factor=1002022.0378.1
ETF-DR + Lossreweighting=Inverse-view2026.0577.9
ETF-DR + Loss + LRreweighting=Inverse-view, LR Schedule=MiLeLR2026.0577.9
SSPBackbone=ResNet-32, Training Epochs=2002024.0377.8
KCLVenue=ICLR212026.0577.6
Focal-SAMVenue=ICML252026.0577.2
LDAMBackbone=ResNet-32, Imbalanced Factor=1002022.0377.1
LDAM-DRWBackbone=ResNet-32, Training Epochs=2002024.0377
ETF-DRVenue=NeurIPS222026.0576.5
IP-DPPVenue=NeurIPS252026.0576.4
CE*reproduced=true2026.0576
CB Loss + CRBackbone Net=ResNet-322023.0375.8
SELVenue=ICCV252026.0575.8
MLLM-LLaVA-FLType=Our framework2024.0975.49
CMOVenue=CVPR22, reproduced=true2026.0574.8
DisAVenue=ICML242026.0574.7
CB-FocalBackbone=ResNet-32, Training Epochs=2002024.0374.6
CB LossBackbone Net=ResNet-322023.0374.5
CLIP2FLType=SOTA2024.0973.37
Cross Entropy + CRBackbone Net=ResNet-322023.0372.6
Focal Loss + CRBackbone Net=ResNet-322023.0371.8
CReFFType=Classifier-retraining2024.0970.55
Cross EntropyBackbone Net=ResNet-322023.0370.3
Focal LossBackbone Net=ResNet-322023.0370.3
CCVRType=Heterogeneity-oriented FL methods2024.0969.53
Ratio LossType=Imbalance-oriented FL methods2024.0959.75
FedNovaType=Heterogeneity-oriented FL methods2024.0957.79
FedProxType=Heterogeneity-oriented FL methods2024.0956.92
FedAvgType=Heterogeneity-oriented FL methods2024.0956.17
FedBEType=Heterogeneity-oriented FL methods2024.0955.79
FedDFType=Heterogeneity-oriented FL methods2024.0955.15
Fed-Focal LossType=Imbalance-oriented FL methods2024.0953.83
FedAvgMType=Heterogeneity-oriented FL methods2024.0952.03
FedAvg+ τ-normType=Imbalance-oriented FL methods2024.0949.95