OpenCodePapers

image-classification-on-mnist

Image Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodePercentage errorAccuracyTrainable ParametersCross Entropy LossEpochsTop 1 AccuracyModelNameReleaseDate
No Routing Needed Between Capsules✓ Link0.1399.871514187Branching/Merging CNN + Homogeneous Vector Capsules2020-01-24
Ensemble learning in CNN augmented with fully connected subnetworks✓ Link0.1699.84EnsNet (Ensemble learning in CNN augmented with fully connected subnetworks)2020-03-19
Efficient-CapsNet: Capsule Network with Self-Attention Routing✓ Link0.1699.84161824Efficient-CapsNet2021-01-29
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods✓ Link0.1799.831400000SOPCNN (Only a single Model)2020-01-24
RMDL: Random Multimodel Deep Learning for Classification✓ Link0.1899.82RMDL (30 RDLs)2018-05-03
Learning local discrete features in explainable-by-design convolutional neural networks✓ Link0.2099.80743882R-ExplaiNet-22 (single model)2024-10-31
Regularization of Neural Networks using DropConnect✓ Link0.2199.77DropConnect2013-06-13
Multi-column Deep Neural Networks for Image Classification✓ Link0.23MCDNN2012-02-13
APAC: Augmented PAttern Classification with Neural Networks0.23APAC2015-05-13
Batch-normalized Maxout Network in Network✓ Link0.24BNM NiN2015-11-09
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures✓ Link0.25SimpleNetv12016-08-22
Dynamic Routing Between Capsules✓ Link0.25CapsNet2017-10-26
Training Neural Networks with Local Error Signals✓ Link0.26VGG8B + LocalLearning + CO2019-01-20
SpinalNet: Deep Neural Network with Gradual Input✓ Link0.2899.72VGG-5 (Spinal FC)2020-07-07
TextCaps : Handwritten Character Recognition with Very Small Datasets✓ Link0.2999.71TextCaps2019-04-17
A Novel lightweight Convolutional Neural Network, ExquisiteNetV2✓ Link0.2999.71518230ExquisiteNetV22021-05-19
WaveMix: Resource-efficient Token Mixing for Images✓ Link0.29WaveMix-128/72022-03-07
Fractional Max-Pooling✓ Link0.3Fractional MP2014-12-18
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree✓ Link0.3Tree+Max-Avg pooling2015-09-30
Competitive Multi-scale Convolution0.3CMsC2015-11-18
EXACT: How to Train Your Accuracy✓ Link0.33EXACT (M3-CNN)2022-05-19
On Second Order Behaviour in Augmented Neural ODEs✓ Link0.3799.63Second Order Neural Ordinary Differential Equation2020-06-12
Augmented Neural ODEs✓ Link0.3799.63Augmented Neural Ordinary Differential Equation2019-04-02
Deeply-Supervised Nets✓ Link0.4DSN2014-09-18
Convolutional Kernel Networks0.4CKN2014-06-12
Unsupervised Feature Learning with C-SVDDNet0.4C-SVDDNet2014-12-23
Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks0.4HOPE2015-02-03
Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network0.4FLSCNN2015-03-16
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units0.4MIM2015-08-03
All you need is a good init✓ Link0.4Fitnet-LSUV-SVM2015-11-19
Evaluating the Performance of TAAF for image classification models✓ Link0.48%99.52%4216420.018835TAAF-CNN2025-02-13
[]()0.599.51882602Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN)
Maxout Networks✓ Link0.5Maxout Networks2013-02-18
Network In Network✓ Link0.5NiN2013-12-16
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks✓ Link0.5ReNet2015-05-03
Deep Convolutional Neural Networks as Generic Feature Extractors0.5DCNN+GFE2017-10-06
Training Very Deep Networks✓ Link0.5VDN2015-07-22
NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data0.51NeuPDE2019-08-08
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization✓ Link0.53Simple CNN with BaikalCMA loss2019-05-27
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision✓ Link0.5899.42SEER (RegNet10B)2022-02-16
The Convolutional Tsetlin Machine✓ Link0.699.4Convolutional Tsetlin Machine2019-05-23
PCANet: A Simple Deep Learning Baseline for Image Classification?✓ Link0.6PCANet2014-04-14
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization✓ Link0.6DiffPrune (LeNet5)2020-12-07
Deep Fried Convnets✓ Link0.7Deep Fried Convnets2014-12-22
Sparse Activity and Sparse Connectivity in Supervised Learning0.8Sparse Activity and Sparse Connectivity in Supervised Learning2016-03-28
Explaining and Harnessing Adversarial Examples✓ Link0.8Explaining and Harnessing Adversarial Examples2014-12-20
BinaryConnect: Training Deep Neural Networks with binary weights during propagations✓ Link1.0BinaryConnect2015-11-02
Parametric Matrix Models1.0198.99129416Convolutional PMM (Parametric Matrix Model)2024-01-22
Sparse Networks from Scratch: Faster Training without Losing Performance✓ Link1.26LeNet 300-100 (Sparse Momentum)2019-07-10
Convolutional Clustering for Unsupervised Learning1.4Convolutional Clustering2015-11-19
Convolutional Sequence to Sequence Learning✓ Link1.4198.59CNN Model by Som2017-05-08
The Weighted Tsetlin Machine: Compressed Representations with Weighted Clauses✓ Link1.598.5Weighted Tsetlin Machine2019-11-28
On the Ideal Number of Groups for Isometric Gradient Propagation1.67MLP (ideal number of groups)2023-02-07
Tensorizing Neural Networks✓ Link1.898.2Perceptron with a tensor train layer2015-09-22
Augmented Neural ODEs✓ Link1.898.2ANODE2019-04-02
The Tsetlin Machine - A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic✓ Link1.898.2Tsetlin Machine2018-04-04
A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification✓ Link1.9698.04GECCO2024-02-01
Parametric Matrix Models2.6297.384990PMM (Parametric Matrix Model)2024-01-22
Trainable Activations for Image Classification✓ Link2.897.2575051DNN-5 (Trainable Activations)2023-01-26
Trainable Activations for Image Classification✓ Link3.097.0386719DNN-3 (Trainable Activations)2023-01-26
Trainable Activations for Image Classification✓ Link3.696.4311651DNN-2 (Trainable Activations)2023-01-26
Stacked What-Where Auto-encoders✓ Link4.76Zhao et al. (2015) (auto-encoder)2015-06-08
ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections5.095.0ProjectionNet2017-08-02
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems✓ Link99.75µ2Net (ViT-L/16)2022-05-25
XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks✓ Link99.68MobileNet_XnODR2021-11-21
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters✓ Link99.68ResNet-92022-03-29
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification✓ Link99.47LR-Net2022-07-19
Learning in Wilson-Cowan model for metapopulation✓ Link99.31CNN+ Wilson-Cowan model RNN2024-06-24
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks✓ Link99.3FastSNN (CNN)2022-05-30
rKAN: Rational Kolmogorov-Arnold Networks✓ Link99.293rKAN2024-06-20
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent✓ Link99.27CNN-5 Layer2021-06-16
fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions✓ Link99.228fKAN2024-06-11
Spike time displacement based error backpropagation in convolutional spiking neural networks99.2StiDi-BP in R-CSNN2021-08-31
Learning in Wilson-Cowan model for metapopulation✓ Link98.13Wilson-Cowan model RNN2024-06-24
Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines98.13Hypervector Tsetlin Machine2024-06-04
[]()98.031208586ViT-Mini_D9
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks✓ Link97.91FastSNN (MLP)2022-05-30
The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware✓ Link96.2Binarized MLP with on-chip spiking backpropagation (on Loihi)2021-06-13
Improving k-Means Clustering Performance with Disentangled Internal Representations✓ Link95.5SNNL-52020-06-05
Personalized Federated Learning with Hidden Information on Personalized Prior92.47pFedBreD_ns_mg2022-11-19
Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces✓ Link70DGMMC-S2024-10-17
Check out how to contribute new results.