Image Classification on MNIST (val)
99.82AccuracyCCT-7/3x1
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| CCT-7/3x1# Params=3.76 M, MACs=1.19 G2021.04 | 99.82 | — | — | — | — | — | — | — | |
| ResNet18# Params=11.18 M, MACs=0.04 G2021.04 | 99.8 | — | — | — | — | — | — | — | |
| ResNet34# Params=21.29 M, MACs=0.08 G2021.04 | 99.77 | — | — | — | — | — | — | — | |
| ViT-Lite-7/4# Params=3.72 M, MACs=0.26 G2021.04 | 99.77 | — | — | — | — | — | — | — | |
| CVT-7/4# Params=3.72 M, MACs=0.25 G2021.04 | 99.76 | — | — | — | — | — | — | — | |
| CCT-7/3x2# Params=3.85 M, MACs=0.29 G2021.04 | 99.76 | — | — | — | — | — | — | — | |
| MobileNetV2/2.0# Params=8.72 M, MACs=0.02 G2021.04 | 99.75 | — | — | — | — | — | — | — | |
| PLIFOptimizable parameters=13.2M2025.12 | 99.72 | — | — | — | — | — | — | — | |
| MobileNetV2/0.5# Params=0.70 M, MACs=< 0.01 G2021.04 | 99.7 | — | — | — | — | — | — | — | |
| CVT-7/8# Params=3.74 M, MACs=0.06 G2021.04 | 99.7 | — | — | — | — | — | — | — | |
| CCT-2/3x2# Params=0.28 M, MACs=0.04 G2021.04 | 99.7 | — | — | — | — | — | — | — | |
| ViT-Lite-7/8# Params=3.74 M, MACs=0.06 G2021.04 | 99.69 | — | — | — | — | — | — | — | |
| ViT-Lite-7/16# Params=3.89 M, MACs=0.02 G2021.04 | 99.68 | — | — | — | — | — | — | — | |
| ViT-12/16# Params=85.63 M, MACs=0.43 G2021.04 | 99.63 | — | — | — | — | — | — | — | |
| ST-RSBP (15C5-P2-40C5-P2-300)Optimizable parameters=784,4802025.12 | 99.62 | — | — | — | — | — | — | — | |
| ResNet110# Params=1.73 M, MACs=0.26 G2021.04 | 99.28 | — | — | — | — | — | — | — | |
| ResNet56# Params=0.85 M, MACs=0.13 G2021.04 | 99.27 | — | — | — | — | — | — | — | |
| SCRAEModel Input=SCRAE2026.03 | 99.25 | 6.8 | — | — | — | — | — | — | |
| LISNNOptimizable parameters=272,4162025.12 | 99.05 | — | — | — | — | — | — | — | |
| ANN-ResNet18Optimizable parameters=11.8M2025.12 | 98.89 | — | — | — | — | — | — | — | |
| SEW-ResNet18 (ADD)Optimizable parameters=11.8M2025.12 | 98.62 | — | — | — | — | — | — | — | |
| BPNumber of hidden layers=32023.10 | 98.2 | — | — | — | — | — | — | — | |
| ANN-ResNet34Optimizable parameters=21.8M2025.12 | 98.01 | — | — | — | — | — | — | — | |
| BPNumber of hidden layers=12023.10 | 98 | — | — | — | — | — | — | — | |
| Exact inverse (Avg J)Number of hidden layers=12023.10 | 97.6 | — | — | — | — | — | — | — | |
| Exact inverseNumber of hidden layers=12023.10 | 97.5 | — | — | — | — | — | — | — | |
| Exact inverseNumber of hidden layers=32023.10 | 97.5 | — | — | — | — | — | — | — | |
| FldzhyanMesh=784x784, Epochs=150, Batch Size=512, Learning Rate=0.0000382025.12 | 97.16 | — | — | — | — | — | — | — | |
| ClementsMesh=784x784, Epochs=150, Batch Size=512, Learning Rate=0.0000382025.12 | 97.03 | — | — | — | — | — | — | — | |
| Linear thresholdNumber of hidden layers=12023.10 | 96.9 | — | — | — | — | — | — | — | |
| Exact inverse (Avg J)Number of hidden layers=32023.10 | 96.9 | — | — | — | — | — | — | — | |
| Linear thresholdNumber of hidden layers=32023.10 | 96.4 | — | — | — | — | — | — | — | |
| Linear threshold (Avg J)Number of hidden layers=12023.10 | 96.4 | — | — | — | — | — | — | — | |
| Clements BellMesh=784x784, Epochs=150, Batch Size=512, Learning Rate=0.0000382025.12 | 96.06 | — | — | — | — | — | — | — | |
| Linear threshold (Avg J)Number of hidden layers=32023.10 | 95.8 | — | — | — | — | — | — | — | |
| Fldzhyan BellMesh=784x784, Epochs=150, Batch Size=512, Learning Rate=0.0000382025.12 | 94.86 | — | — | — | — | — | — | — | |
| Raw DataModel Input=Raw Data2026.03 | 92.45 | 0 | — | — | — | — | — | — | |
| FedVTCDir=12025.08 | 90.1 | — | — | — | — | — | — | — | |
| FedVTCDir=0.12025.08 | 88.7 | — | — | — | — | — | — | — | |
| SQDR-CNN[4b-9q]Optimizable parameters=8572025.12 | 88.32 | — | — | — | — | — | — | — | |
| SQDR-CNN[4b-18q]Optimizable parameters=1,2982025.12 | 88.32 | — | — | — | — | — | — | — | |
| Base AEModel Input=Base AE2026.03 | 88.1 | -4.35 | — | — | — | — | — | — | |
| pFedAFMDir=12025.08 | 87.2 | — | — | — | — | — | — | — | |
| FedTGPDir=12025.08 | 86.8 | — | — | — | — | — | — | — | |
| FedTypeDir=12025.08 | 86.7 | — | — | — | — | — | — | — | |
| SQDR-CNN[2b-18q]Optimizable parameters=1,1902025.12 | 86.55 | — | — | — | — | — | — | — | |
| CCVRDir=12025.08 | 86.2 | — | — | — | — | — | — | — | |
| FedProtoDir=12025.08 | 86.1 | — | — | — | — | — | — | — | |
| pFedAFMDir=0.12025.08 | 85.6 | — | — | — | — | — | — | — | |
| CCVRDir=0.12025.08 | 85.5 | — | — | — | — | — | — | — | |
| FedTGPDir=0.12025.08 | 85.4 | — | — | — | — | — | — | — | |
| SQDR-CNN[2b-9q]Optimizable parameters=8032025.12 | 84.03 | — | — | — | — | — | — | — | |
| FedTypeDir=0.12025.08 | 83.9 | — | — | — | — | — | — | — | |
| FedProtoDir=0.12025.08 | 83.4 | — | — | — | — | — | — | — | |
| FedGenDir=12025.08 | 81.9 | — | — | — | — | — | — | — | |
| FedGenDir=0.12025.08 | 81.1 | — | — | — | — | — | — | — | |
| Spiking-ResNet34Optimizable parameters=21.8M2025.12 | 69.02 | — | — | — | — | — | — | — | |
| Spiking-ResNet50Optimizable parameters=25.6M2025.12 | 13.45 | — | — | — | — | — | — | — | |
| CTMd_model=256, Backbone=HRF, Steps=200K, Seeding Protocol=single seed2026.05 | — | — | 99.59 | — | — | — | — | — | |
| TIDEd_model=256, Backbone=HRF, Steps=50K, Seeding Protocol=multi-seeded2026.05 | — | — | 99.67 | 99.63 | 99.62 | 0.04 | 99.59 | 0.06 |