Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MNIST

Benchmarks

Task NameDataset NameSOTA ResultTrend
Image ClassificationMNIST (test)
Accuracy99.35
894
Image ClassificationMNIST
Accuracy99.87
417
Image ClassificationMNIST
Accuracy100
398
Image ClassificationMNIST (test)
Accuracy99.6
201
Image ClassificationMNIST (test)
Test Accuracy99.67
189
Image ClassificationMNIST (test)
Accuracy98.15
177
Image ClassificationMNIST non-IID (test)
Accuracy98.92
139
Image ClassificationMNIST (test)
Accuracy99.7
138
ClusteringMNIST (test)
NMI0.97
136
Graph ClassificationMNIST (test)
Accuracy98.8
121
ClusteringMNIST
NMI0.978
113
Backdoor CertificationMNIST (test)
AER1.81
112
Image ClassificationMNIST (train)
Train Accuracy100
107
Image ClassificationMNIST rotated (test)
Test Error (%)0.59
105
Graph classificationMNIST
Accuracy99.2
103
Image GenerationMNIST Binary (test)
FID4.69
98
ClusteringMNIST (full)
Accuracy98.7
98
Digit ClassificationMNIST (test)
Error Rate0.21
94
Anomaly DetectionMNIST
AUC100
90
ClassificationMNIST
Accuracy99.3
89
Backdoor AttackMNIST (test)
Classification Accuracy (C-Acc)99.89
88
Federated Learning ClassificationMNIST FedAvg 0.962 (test)
Accuracy96.2
88
Anomaly DetectionMNIST
AUC99.35
87
Image ClassificationMNIST VAE m=32 latent space (test)
Accuracy98.29
85
Image GenerationMNIST
FID1.02
85
Showing 25 of 1280 rows
...