List your company
ResearchFormerly WizWand

Image Classification on ANIMAL-10N

0.9252AccuracyIndividual
0.1619440.3600970.558250.756403Jul 21, 2022Feb 12, 2023Sep 7, 2023Mar 31, 2024Oct 24, 2024May 18, 2025Dec 11, 2025
Updated 4mo ago

Evaluation results

MethodLinks
IndividualBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=12024.050.9252
ProMixBackbone=VGG-192022.070.8998
LaT-IBCategory=Ours2025.120.8849
EMR-MERGINGBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.877
Jo-SNC-SEMPublication=Ours2025.080.8719
Dynamic Loss2022.110.8654
Jo-SNCPublication=IEEE TPAMI 20252025.080.8617
(ELR+)+VIBCategory=Denoise + IB2025.120.8587
Promix+VIBCategory=Denoise + IB2025.120.8547
CMW-Net2022.110.847
GJS2022.110.8417
NCTBackbone=VGG-192022.070.841
NCT2022.110.841
DivdeMix2022.110.84
SIBCategory=Improved IB2025.120.8395
SELCBackbone=VGG-192022.070.837
PLCBackbone=VGG-192022.070.834
PLC2022.110.834
PLCPublication=ICLR 20212025.080.834
AdaptCDRPPublication=NeurIPS 20242025.080.8308
JAL-SEMPublication=Ours2025.080.827
IP EnsembleBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8235
LiSSABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8193
Self-TracInBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8182
SELFIEBackbone=VGG-192022.070.818
SELFIE2022.110.818
SELFIEPublication=ICML 20192025.080.818
VIB (LGCE)Category=Robust Loss2025.120.8172
JAL*Publication=ICCV 20252025.080.8168
DataInfBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.816
CE-SEMPublication=Ours2025.080.8142
Self-LiSSABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8123
IPBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8119
EKFACBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8089
GEXBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8078
TDABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8057
Cross EntropyBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8054
Co-teaching2022.110.802
Co-teachingPublication=NeurIPS 20182025.080.802
TracInBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.050.8012
CEBackbone=VGG-192022.070.794
Cross Entropy2022.110.794
CEPublication=N/A2025.080.794
DT-JSCCCategory=Improved IB2025.120.7898
VIB (LSCE)Category=Robust Loss2025.120.7717
VIBCategory=Classic IB2025.120.7628
NIBCategory=Classic IB2025.120.7562
JoCoR+VIBCategory=Denoise + IB2025.120.7545
RegMeanBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.6874
AdaMergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.6655
Task ArithmeticBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.5114
Weight AveragingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.46
Ties-MergingBackbone=ViT-B/16, Pre-trained=ImageNet-21k, Number of Merged Models=302024.050.1913