Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Image Classification
/
Kuzushiji-MNIST
Image Classification on Kuzushiji-MNIST
Metric: Accuracy (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Accuracy (best first)
Accuracy (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Accuracy
▼
Extra Data
Paper
Date
↕
Code
1
KMNIST-Tiny
99.35
No
-
-
Code
2
KMNIST-Mobile
99.29
No
-
-
Code
3
VGG-5 (Spinal FC)
99.15
No
SpinalNet: Deep Neural Network with Gradual Input
2020-07-07
Code
4
CAMNet3
99.05
No
Context-Aware Multipath Networks
2019-07-26
-
5
VGG8B(2x) + LocalLearning + CO
99.01
No
Training Neural Networks with Local Error Signals
2019-01-20
Code
6
VGG-5
98.98
No
ProgressiveSpinalNet architecture for FC layers
2021-03-21
Code
7
CN(d=32)
98.84
No
-
-
-
8
NSRL (log D) (d=16)
98.81
No
-
-
-
9
CN(d=16)
98.8
No
-
-
-
10
Resnet-152
98.79
No
A Comprehensive Study of ImageNet Pre-Training f...
2019-05-22
-
11
R-ExplaiNet-26
98.78
No
Learning local discrete features in explainable-...
2024-10-31
Code
12
ResNet-14
98.75
No
CNN Filter DB: An Empirical Investigation of Tra...
2022-03-29
Code
13
NSRL (WGAN) (d=32)
98.72
No
-
-
-
14
NSRL (WGAN) (d=8)
98.68
No
-
-
-
15
NSRL (WGAN) (d=16)
98.66
No
-
-
-
16
NSRL (log D) (d=32)
98.63
No
-
-
-
17
NSRL (log D) (d=8)
98.61
No
-
-
-
18
CN(d=8)
98.6
No
-
-
-
19
Efficient Capsnet
98.43
No
-
-
Code
20
PreActResNet-18 + Input Mixup
98.41
No
mixup: Beyond Empirical Risk Minimization
2017-10-25
Code
21
PreActResNet-18
97.82
No
Identity Mappings in Deep Residual Networks
2016-03-16
Code
22
Convolutional Tsetlin Machine
96.3
No
The Convolutional Tsetlin Machine
2019-05-23
Code
23
KerCNN
93.13
No
KerCNNs: biologically inspired lateral connectio...
2019-10-18
-
24
linear/flexible model
79.9
No
Multi-Complementary and Unlabeled Learning for A...
2020-01-13
-
25
FWD
79.5
No
Multi-Complementary and Unlabeled Learning for A...
2020-01-13
-
26
Complementary-Label Learning
67.1
No
Complementary-Label Learning for Arbitrary Losse...
2018-10-10
Code
#1
KMNIST-Tiny
99.35
Accuracy
No paper
Code
#2
KMNIST-Mobile
99.29
Accuracy
No paper
Code
#3
VGG-5 (Spinal FC)
SOTA
99.15
Accuracy
· 2020-07-07
SpinalNet: Deep Neural Network with Gradual Input
Code
#4
CAMNet3
SOTA
99.05
Accuracy
· 2019-07-26
Context-Aware Multipath Networks
#5
VGG8B(2x) + LocalLearning + CO
SOTA
99.01
Accuracy
· 2019-01-20
Training Neural Networks with Local Error Signals
Code
#6
VGG-5
98.98
Accuracy
· 2021-03-21
ProgressiveSpinalNet architecture for FC layers
Code
#7
CN(d=32)
98.84
Accuracy
No paper
#8
NSRL (log D) (d=16)
98.81
Accuracy
No paper
#9
CN(d=16)
98.8
Accuracy
No paper
#10
Resnet-152
98.79
Accuracy
· 2019-05-22
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
#11
R-ExplaiNet-26
98.78
Accuracy
· 2024-10-31
Learning local discrete features in explainable-by-design convolutional neural networks
Code
#12
ResNet-14
98.75
Accuracy
· 2022-03-29
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
Code
#13
NSRL (WGAN) (d=32)
98.72
Accuracy
No paper
#14
NSRL (WGAN) (d=8)
98.68
Accuracy
No paper
#15
NSRL (WGAN) (d=16)
98.66
Accuracy
No paper
#16
NSRL (log D) (d=32)
98.63
Accuracy
No paper
#17
NSRL (log D) (d=8)
98.61
Accuracy
No paper
#18
CN(d=8)
98.6
Accuracy
No paper
#19
Efficient Capsnet
98.43
Accuracy
No paper
Code
#20
PreActResNet-18 + Input Mixup
SOTA
98.41
Accuracy
· 2017-10-25
mixup: Beyond Empirical Risk Minimization
Code
#21
PreActResNet-18
SOTA
97.82
Accuracy
· 2016-03-16
Identity Mappings in Deep Residual Networks
Code
#22
Convolutional Tsetlin Machine
96.3
Accuracy
· 2019-05-23
The Convolutional Tsetlin Machine
Code
#23
KerCNN
93.13
Accuracy
· 2019-10-18
KerCNNs: biologically inspired lateral connections for classification of corrupted images
#24
linear/flexible model
79.9
Accuracy
· 2020-01-13
Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models
#25
FWD
79.5
Accuracy
· 2020-01-13
Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models
#26
Complementary-Label Learning
67.1
Accuracy
· 2018-10-10
Complementary-Label Learning for Arbitrary Losses and Models
Code