Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Image Classification
/
MNIST
Image Classification on 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
Branching/Merging CNN + Homogeneous Vector Capsules
99.87
No
No Routing Needed Between Capsules
2020-01-24
Code
2
EnsNet (Ensemble learning in CNN augmented with fully connected subnetworks)
99.84
No
Ensemble learning in CNN augmented with fully co...
2020-03-19
Code
3
Efficient-CapsNet
99.84
No
Efficient-CapsNet: Capsule Network with Self-Att...
2021-01-29
Code
4
SOPCNN (Only a single Model)
99.83
No
Stochastic Optimization of Plain Convolutional N...
2020-01-24
Code
5
RMDL (30 RDLs)
99.82
No
RMDL: Random Multimodel Deep Learning for Classi...
2018-05-03
Code
6
R-ExplaiNet-22 (single model)
99.8
No
Learning local discrete features in explainable-...
2024-10-31
Code
7
DropConnect
99.77
No
-
-
Code
8
µ2Net (ViT-L/16)
99.75
No
An Evolutionary Approach to Dynamic Introduction...
2022-05-25
Code
9
VGG-5 (Spinal FC)
99.72
No
SpinalNet: Deep Neural Network with Gradual Input
2020-07-07
Code
10
TextCaps
99.71
No
TextCaps : Handwritten Character Recognition wit...
2019-04-17
Code
11
ExquisiteNetV2
99.71
No
A Novel lightweight Convolutional Neural Network...
2021-05-19
Code
12
MobileNet_XnODR
99.68
No
XnODR and XnIDR: Two Accurate and Fast Fully Con...
2021-11-21
Code
13
ResNet-9
99.68
No
CNN Filter DB: An Empirical Investigation of Tra...
2022-03-29
Code
14
Second Order Neural Ordinary Differential Equation
99.63
No
On Second Order Behaviour in Augmented Neural ODEs
2020-06-12
Code
15
Augmented Neural Ordinary Differential Equation
99.63
No
Augmented Neural ODEs
2019-04-02
Code
16
Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN)
99.5
No
-
-
-
17
LR-Net
99.47
No
LR-Net: A Block-based Convolutional Neural Netwo...
2022-07-19
Code
18
SEER (RegNet10B)
99.42
No
Vision Models Are More Robust And Fair When Pret...
2022-02-16
Code
19
Convolutional Tsetlin Machine
99.4
No
The Convolutional Tsetlin Machine
2019-05-23
Code
20
CNN+ Wilson-Cowan model RNN
99.31
No
Learning in Wilson-Cowan model for metapopulation
2024-06-24
Code
21
FastSNN (CNN)
99.3
No
Robust and accelerated single-spike spiking neur...
2022-05-30
Code
22
IIC
99.3
No
Invariant Information Clustering for Unsupervise...
2018-07-17
Code
23
rKAN
99.293
No
rKAN: Rational Kolmogorov-Arnold Networks
2024-06-20
Code
24
CNN-5 Layer
99.27
No
Robust Training in High Dimensions via Block Coo...
2021-06-16
Code
25
fKAN
99.228
No
fKAN: Fractional Kolmogorov-Arnold Networks with...
2024-06-11
Code
26
StiDi-BP in R-CSNN
99.2
No
Spike time displacement based error backpropagat...
2021-08-31
-
27
Convolutional PMM (Parametric Matrix Model)
98.99
No
Parametric Matrix Models
2024-01-22
-
28
CNN Model by Som
98.59
No
Convolutional Sequence to Sequence Learning
2017-05-08
Code
29
Weighted Tsetlin Machine
98.5
No
The Weighted Tsetlin Machine: Compressed Represe...
2019-11-28
Code
30
ACOL + GAR + k-means
98.32
No
Learning Latent Representations in Neural Networ...
2018-02-08
-
31
Perceptron with a tensor train layer
98.2
No
Tensorizing Neural Networks
2015-09-22
Code
32
ANODE
98.2
No
Augmented Neural ODEs
2019-04-02
Code
33
Tsetlin Machine
98.2
No
The Tsetlin Machine - A Game Theoretic Bandit Dr...
2018-04-04
Code
34
Vanilla FC layer only
98.19
No
ProgressiveSpinalNet architecture for FC layers
2021-03-21
Code
35
Wilson-Cowan model RNN
98.13
No
Learning in Wilson-Cowan model for metapopulation
2024-06-24
Code
36
Hypervector Tsetlin Machine
98.13
No
Exploring Effects of Hyperdimensional Vectors fo...
2024-06-04
-
37
GECCO
98.04
No
A Single Graph Convolution Is All You Need: Effi...
2024-02-01
Code
38
ViT-Mini_D9
98.03
No
-
-
-
39
FastSNN (MLP)
97.91
No
Robust and accelerated single-spike spiking neur...
2022-05-30
Code
40
TURTLE (CLIP + DINOv2)
97.8
No
Let Go of Your Labels with Unsupervised Transfer
2024-06-11
Code
41
PMM (Parametric Matrix Model)
97.38
No
Parametric Matrix Models
2024-01-22
-
42
DTI-Clustering
97.3
No
Deep Transformation-Invariant Clustering
2020-06-19
Code
43
DNN-5 (Trainable Activations)
97.2
No
-
-
Code
44
DNN-3 (Trainable Activations)
97
No
-
-
Code
45
VMM
96.74
No
The VampPrior Mixture Model
2024-02-06
Code
46
Bidirectional InfoGAN
96.61
No
Inferencing Based on Unsupervised Learning of Di...
2018-03-07
Code
47
DNN-2 (Trainable Activations)
96.4
No
-
-
Code
48
Binarized MLP with on-chip spiking backpropagation (on Loihi)
96.2
No
The Backpropagation Algorithm Implemented on Spi...
2021-06-13
Code
49
Adversarial AE
95.9
No
Adversarial Autoencoders
2015-11-18
Code
50
CatGAN
95.73
No
Unsupervised and Semi-supervised Learning with C...
2015-11-19
Code
51
SNNL-5
95.5
No
Improving k-Means Clustering Performance with Di...
2020-06-05
Code
52
ProjectionNet
95
No
ProjectionNet: Learning Efficient On-Device Deep...
2017-08-02
-
53
InfoGAN
95
No
InfoGAN: Interpretable Representation Learning b...
2016-06-12
Code
54
PixelGAN Autoencoders
94.73
No
PixelGAN Autoencoders
2017-06-02
Code
55
pFedBreD_ns_mg
92.47
No
Personalized Federated Learning with Hidden Info...
2022-11-19
-
#1
Branching/Merging CNN + Homogeneous Vector Capsules
SOTA
99.87
Accuracy
· 2020-01-24
No Routing Needed Between Capsules
Code
#2
EnsNet (Ensemble learning in CNN augmented with fully connected subnetworks)
99.84
Accuracy
· 2020-03-19
Ensemble learning in CNN augmented with fully connected subnetworks
Code
#3
Efficient-CapsNet
99.84
Accuracy
· 2021-01-29
Efficient-CapsNet: Capsule Network with Self-Attention Routing
Code
#4
SOPCNN (Only a single Model)
99.83
Accuracy
· 2020-01-24
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods
Code
#5
RMDL (30 RDLs)
SOTA
99.82
Accuracy
· 2018-05-03
RMDL: Random Multimodel Deep Learning for Classification
Code
#6
R-ExplaiNet-22 (single model)
99.8
Accuracy
· 2024-10-31
Learning local discrete features in explainable-by-design convolutional neural networks
Code
#7
DropConnect
99.77
Accuracy
No paper
Code
#8
µ2Net (ViT-L/16)
99.75
Accuracy
· 2022-05-25
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
Code
#9
VGG-5 (Spinal FC)
99.72
Accuracy
· 2020-07-07
SpinalNet: Deep Neural Network with Gradual Input
Code
#10
TextCaps
99.71
Accuracy
· 2019-04-17
TextCaps : Handwritten Character Recognition with Very Small Datasets
Code
#11
ExquisiteNetV2
99.71
Accuracy
· 2021-05-19
A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
Code
#12
MobileNet_XnODR
99.68
Accuracy
· 2021-11-21
XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks
Code
#13
ResNet-9
99.68
Accuracy
· 2022-03-29
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
Code
#14
Second Order Neural Ordinary Differential Equation
99.63
Accuracy
· 2020-06-12
On Second Order Behaviour in Augmented Neural ODEs
Code
#15
Augmented Neural Ordinary Differential Equation
99.63
Accuracy
· 2019-04-02
Augmented Neural ODEs
Code
#16
Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN)
99.5
Accuracy
No paper
#17
LR-Net
99.47
Accuracy
· 2022-07-19
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification
Code
#18
SEER (RegNet10B)
99.42
Accuracy
· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
Code
#19
Convolutional Tsetlin Machine
99.4
Accuracy
· 2019-05-23
The Convolutional Tsetlin Machine
Code
#20
CNN+ Wilson-Cowan model RNN
99.31
Accuracy
· 2024-06-24
Learning in Wilson-Cowan model for metapopulation
Code
#21
FastSNN (CNN)
99.3
Accuracy
· 2022-05-30
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks
Code
#22
IIC
99.3
Accuracy
· 2018-07-17
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
Code
#23
rKAN
99.293
Accuracy
· 2024-06-20
rKAN: Rational Kolmogorov-Arnold Networks
Code
#24
CNN-5 Layer
99.27
Accuracy
· 2021-06-16
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
Code
#25
fKAN
99.228
Accuracy
· 2024-06-11
fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions
Code
#26
StiDi-BP in R-CSNN
99.2
Accuracy
· 2021-08-31
Spike time displacement based error backpropagation in convolutional spiking neural networks
#27
Convolutional PMM (Parametric Matrix Model)
98.99
Accuracy
· 2024-01-22
Parametric Matrix Models
#28
CNN Model by Som
SOTA
98.59
Accuracy
· 2017-05-08
Convolutional Sequence to Sequence Learning
Code
#29
Weighted Tsetlin Machine
98.5
Accuracy
· 2019-11-28
The Weighted Tsetlin Machine: Compressed Representations with Weighted Clauses
Code
#30
ACOL + GAR + k-means
98.32
Accuracy
· 2018-02-08
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
#31
Perceptron with a tensor train layer
SOTA
98.2
Accuracy
· 2015-09-22
Tensorizing Neural Networks
Code
#32
ANODE
98.2
Accuracy
· 2019-04-02
Augmented Neural ODEs
Code
#33
Tsetlin Machine
98.2
Accuracy
· 2018-04-04
The Tsetlin Machine - A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic
Code
#34
Vanilla FC layer only
98.19
Accuracy
· 2021-03-21
ProgressiveSpinalNet architecture for FC layers
Code
#35
Wilson-Cowan model RNN
98.13
Accuracy
· 2024-06-24
Learning in Wilson-Cowan model for metapopulation
Code
#36
Hypervector Tsetlin Machine
98.13
Accuracy
· 2024-06-04
Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines
#37
GECCO
98.04
Accuracy
· 2024-02-01
A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification
Code
#38
ViT-Mini_D9
98.03
Accuracy
No paper
#39
FastSNN (MLP)
97.91
Accuracy
· 2022-05-30
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks
Code
#40
TURTLE (CLIP + DINOv2)
97.8
Accuracy
· 2024-06-11
Let Go of Your Labels with Unsupervised Transfer
Code
#41
PMM (Parametric Matrix Model)
97.38
Accuracy
· 2024-01-22
Parametric Matrix Models
#42
DTI-Clustering
97.3
Accuracy
· 2020-06-19
Deep Transformation-Invariant Clustering
Code
#43
DNN-5 (Trainable Activations)
97.2
Accuracy
No paper
Code
#44
DNN-3 (Trainable Activations)
97
Accuracy
No paper
Code
#45
VMM
96.74
Accuracy
· 2024-02-06
The VampPrior Mixture Model
Code
#46
Bidirectional InfoGAN
96.61
Accuracy
· 2018-03-07
Inferencing Based on Unsupervised Learning of Disentangled Representations
Code
#47
DNN-2 (Trainable Activations)
96.4
Accuracy
No paper
Code
#48
Binarized MLP with on-chip spiking backpropagation (on Loihi)
96.2
Accuracy
· 2021-06-13
The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware
Code
#49
Adversarial AE
95.9
Accuracy
· 2015-11-18
Adversarial Autoencoders
Code
#50
CatGAN
95.73
Accuracy
· 2015-11-19
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Code
#51
SNNL-5
95.5
Accuracy
· 2020-06-05
Improving k-Means Clustering Performance with Disentangled Internal Representations
Code
#52
ProjectionNet
95
Accuracy
· 2017-08-02
ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
#53
InfoGAN
95
Accuracy
· 2016-06-12
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Code
#54
PixelGAN Autoencoders
94.73
Accuracy
· 2017-06-02
PixelGAN Autoencoders
Code
#55
pFedBreD_ns_mg
92.47
Accuracy
· 2022-11-19
Personalized Federated Learning with Hidden Information on Personalized Prior