List your company
ResearchFormerly WizWand

Image Classification on ImageNet 1K (val) (Top-1 Accuracy and Power)

82.96Top-1 AccuracyMSViT
69.731273.165676.680.0344May 8, 2026
Updated 6mo ago

Evaluation results

MethodLinks
MSViTType=SNN, Architecture=MSViT-10-512, Param (M)=30.23, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0582.9624.74
DeiTType=ANN, Architecture=DeiT-B, Param (M)=86.59, Time Step=1, Input Size=224 x 224, Knowledge Distillation=false2026.0581.880.5
SAFformerType=SNN, Architecture=SAFformer-10-512, Param (M)=26.58, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=false2026.0580.445.88
MSViTType=SNN, Architecture=MSViT-10-384, Param (M)=17.69, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0580.0916.65
Max-FormerType=SNN, Architecture=Max-10-512, Param (M)=28.65, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0579.867.49
DeiTType=ANN, Architecture=DeiT-S, Param (M)=22.00, Time Step=1, Input Size=224 x 224, Knowledge Distillation=false2026.0579.821.2
E-SpikeFormerType=SNN, Architecture=E-SpikeFormer-M, Param (M)=19.00, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=false2026.0579.85.9
SAFformerType=SNN, Architecture=SAFformer-10-384, Param (M)=15.12, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=false2026.0579.193.75
QSD-TransformerType=SNN, Architecture=S-Transformer v2-M†, Param (M)=3.90, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=true2026.0578.95.7
STAType=A2S, Architecture=ViT-B/32, Param (M)=86.00, Time Step=32, Input Size=224 x 224, Knowledge Distillation=false2026.0578.72—
MSTType=A2S, Architecture=Swin Transformer-T, Param (M)=28.50, Time Step=512, Input Size=224 x 224, Knowledge Distillation=false2026.0578.51—
E-SpikeFormerType=SNN, Architecture=E-SpikeFormer-S, Param (M)=10.00, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=false2026.0578.53
Max-FormerType=SNN, Architecture=Max-10-384, Param (M)=16.23, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0577.824.89
QSD-TransformerType=SNN, Architecture=S-Transformer v2-T†, Param (M)=1.80, Time Step=1×4, Input Size=224 x 224, Knowledge Distillation=true2026.0577.52.5
S-Transformer v2Type=SNN, Architecture=S-Transformer v2-8-512, Param (M)=31.30, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0577.232.8
S-Transformer v2Type=SNN, Architecture=S-Transformer v2-8-384, Param (M)=15.10, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0574.116.7
SpikformerType=SNN, Architecture=Spikformer-8-512, Param (M)=29.68, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0573.3811.58
SpikformerType=SNN, Architecture=Spikformer-8-384, Param (M)=16.81, Time Step=4×1, Input Size=224 x 224, Knowledge Distillation=false2026.0570.247.73