{"url":"/sota/image-classification-on-mnist","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"MNIST","url":"/dataset/mnist"},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"**Image Classification** is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike [object detection](/task/object-detection), which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as [image retrieval](/task/image-retrieval), which also involves finding similar images in a large database.\r\n\r\n\r\n<span class=\"description-source\">Source: [Metamorphic Testing for Object Detection Systems ](https://arxiv.org/abs/1912.12162)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Percentage error","Accuracy","Trainable Parameters","Cross Entropy Loss","Epochs","Top 1 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Percentage error":"lower","Accuracy":"higher","Trainable Parameters":null,"Cross Entropy Loss":"lower","Epochs":null,"Top 1 Accuracy":"higher"}},"counts":{"rows":81,"rows_with_code":61,"rows_with_paper_page":79,"rows_dated":79,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Branching/Merging CNN + Homogeneous Vector Capsules","metrics":{"Accuracy":"99.87","Percentage error":"0.13","Trainable Parameters":"1514187"},"uses_additional_data":false,"paper_date":"2020-01-24","paper":"/paper/a-branching-and-merging-convolutional-network","paper_url":"https://arxiv.org/abs/2001.09136v6","paper_title":"No Routing Needed Between Capsules","code":"https://github.com/AdamByerly/BMCNNwHFCs","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"EnsNet (Ensemble learning in CNN augmented with fully connected subnetworks)","metrics":{"Accuracy":"99.84","Percentage error":"0.16"},"uses_additional_data":false,"paper_date":"2020-03-19","paper":"/paper/ensemble-learning-in-cnn-augmented-with-fully","paper_url":"https://arxiv.org/abs/2003.08562v3","paper_title":"Ensemble learning in CNN augmented with fully connected subnetworks","code":"https://github.com/eaguaida/TF_EnsNet-","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"Efficient-CapsNet","metrics":{"Accuracy":"99.84","Percentage error":"0.16","Trainable Parameters":"161824"},"uses_additional_data":false,"paper_date":"2021-01-29","paper":"/paper/efficient-capsnet-capsule-network-with-self","paper_url":"https://arxiv.org/abs/2101.12491v2","paper_title":"Efficient-CapsNet: Capsule Network with Self-Attention Routing","code":"https://github.com/EscVM/Efficient-CapsNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"SOPCNN (Only a single Model)","metrics":{"Accuracy":"99.83","Percentage error":"0.17","Trainable Parameters":"1400000"},"uses_additional_data":false,"paper_date":"2020-01-24","paper":"/paper/stochastic-optimization-of-plain","paper_url":"https://arxiv.org/abs/2001.08856v1","paper_title":"Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods","code":"https://github.com/junaidaliop/MNIST-SOPCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"RMDL (30 RDLs)","metrics":{"Accuracy":"99.82","Percentage error":"0.18"},"uses_additional_data":false,"paper_date":"2018-05-03","paper":"/paper/rmdl-random-multimodel-deep-learning-for","paper_url":"http://arxiv.org/abs/1805.01890v2","paper_title":"RMDL: Random Multimodel Deep Learning for Classification","code":"https://github.com/kk7nc/RMDL","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"R-ExplaiNet-22 (single model)","metrics":{"Accuracy":"99.80","Percentage error":"0.20","Trainable Parameters":"743882"},"uses_additional_data":false,"paper_date":"2024-10-31","paper":"/paper/learning-local-discrete-features-in","paper_url":"https://arxiv.org/abs/2411.00139v1","paper_title":"Learning local discrete features in explainable-by-design convolutional neural networks","code":"https://github.com/pikaplan/LearnExplaiNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DropConnect","metrics":{"Accuracy":"99.77","Percentage error":"0.21"},"uses_additional_data":false,"paper_date":"2013-06-13","paper":"/paper/regularization-of-neural-networks-using","paper_url":"http://cds.nyu.edu/projects/regularization-neural-networks-using-dropconnect/","paper_title":"Regularization of Neural Networks using DropConnect","code":"https://github.com/mlpack/mlpack/blob/master/src/mlpack/methods/ann/layer/dropconnect.hpp","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MCDNN","metrics":{"Percentage error":"0.23"},"uses_additional_data":false,"paper_date":"2012-02-13","paper":"/paper/multi-column-deep-neural-networks-for-image","paper_url":"http://arxiv.org/abs/1202.2745v1","paper_title":"Multi-column Deep Neural Networks for Image Classification","code":"https://github.com/hughperkins/DeepCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"APAC","metrics":{"Percentage error":"0.23"},"uses_additional_data":false,"paper_date":"2015-05-13","paper":"/paper/apac-augmented-pattern-classification-with","paper_url":"http://arxiv.org/abs/1505.03229v1","paper_title":"APAC: Augmented PAttern Classification with Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"BNM NiN","metrics":{"Percentage error":"0.24"},"uses_additional_data":false,"paper_date":"2015-11-09","paper":"/paper/batch-normalized-maxout-network-in-network","paper_url":"http://arxiv.org/abs/1511.02583v1","paper_title":"Batch-normalized Maxout Network in Network","code":"https://github.com/JohnBensen1000/machine_learning","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"SimpleNetv1","metrics":{"Percentage error":"0.25"},"uses_additional_data":false,"paper_date":"2016-08-22","paper":"/paper/lets-keep-it-simple-using-simple","paper_url":"https://arxiv.org/abs/1608.06037v8","paper_title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","code":"https://github.com/Coderx7/SimpleNet","n_code_links":9,"syntology":{"n_ran":3,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"CapsNet","metrics":{"Percentage error":"0.25"},"uses_additional_data":false,"paper_date":"2017-10-26","paper":"/paper/dynamic-routing-between-capsules","paper_url":"http://arxiv.org/abs/1710.09829v2","paper_title":"Dynamic Routing Between Capsules","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":77,"syntology":{"n_ran":18,"n_unverified":100,"n_samples":118,"n_pointer_only_licence":12}},{"rank_in_archive_order":13,"model":"VGG8B + LocalLearning + CO","metrics":{"Percentage error":"0.26"},"uses_additional_data":false,"paper_date":"2019-01-20","paper":"/paper/training-neural-networks-with-local-error","paper_url":"https://arxiv.org/abs/1901.06656v2","paper_title":"Training Neural Networks with Local Error Signals","code":"https://github.com/anokland/local-loss","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"VGG-5 (Spinal FC)","metrics":{"Accuracy":"99.72","Percentage error":"0.28"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/spinalnet-deep-neural-network-with-gradual-1","paper_url":"https://arxiv.org/abs/2007.03347v3","paper_title":"SpinalNet: Deep Neural Network with Gradual Input","code":"https://github.com/dipuk0506/SpinalNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":15,"model":"TextCaps","metrics":{"Accuracy":"99.71","Percentage error":"0.29"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/textcaps-handwritten-character-recognition","paper_url":"http://arxiv.org/abs/1904.08095v1","paper_title":"TextCaps : Handwritten Character Recognition with Very Small Datasets","code":"https://github.com/vinojjayasundara/textcaps","n_code_links":3,"syntology":null},{"rank_in_archive_order":16,"model":"ExquisiteNetV2","metrics":{"Accuracy":"99.71","Percentage error":"0.29","Trainable Parameters":"518230"},"uses_additional_data":false,"paper_date":"2021-05-19","paper":"/paper/a-novel-lightweight-convolutional-neural","paper_url":"https://arxiv.org/abs/2105.09008v5","paper_title":"A Novel lightweight Convolutional Neural Network, ExquisiteNetV2","code":"https://github.com/shyhyawJou/ExquisiteNetV2","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"WaveMix-128/7","metrics":{"Percentage error":"0.29"},"uses_additional_data":false,"paper_date":"2022-03-07","paper":"/paper/wavemix-resource-efficient-token-mixing-for","paper_url":"https://arxiv.org/abs/2203.03689v1","paper_title":"WaveMix: Resource-efficient Token Mixing for Images","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Fractional MP","metrics":{"Percentage error":"0.3"},"uses_additional_data":false,"paper_date":"2014-12-18","paper":"/paper/fractional-max-pooling","paper_url":"http://arxiv.org/abs/1412.6071v4","paper_title":"Fractional Max-Pooling","code":"https://github.com/facebookresearch/SparseConvNet","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Tree+Max-Avg pooling","metrics":{"Percentage error":"0.3"},"uses_additional_data":false,"paper_date":"2015-09-30","paper":"/paper/generalizing-pooling-functions-in","paper_url":"http://arxiv.org/abs/1509.08985v2","paper_title":"Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree","code":"https://github.com/cypw/DPNs","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"CMsC","metrics":{"Percentage error":"0.3"},"uses_additional_data":false,"paper_date":"2015-11-18","paper":"/paper/competitive-multi-scale-convolution","paper_url":"http://arxiv.org/abs/1511.05635v1","paper_title":"Competitive Multi-scale Convolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"EXACT (M3-CNN)","metrics":{"Percentage error":"0.33"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/exact-how-to-train-your-accuracy","paper_url":"https://arxiv.org/abs/2205.09615v5","paper_title":"EXACT: How to Train Your Accuracy","code":"https://github.com/tinkoff-ai/exact","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"Second Order Neural Ordinary Differential Equation","metrics":{"Accuracy":"99.63","Percentage error":"0.37"},"uses_additional_data":false,"paper_date":"2020-06-12","paper":"/paper/on-second-order-behaviour-in-augmented-neural","paper_url":"https://arxiv.org/abs/2006.07220v2","paper_title":"On Second Order Behaviour in Augmented Neural ODEs","code":"https://github.com/a-norcliffe/sonode","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"Augmented Neural Ordinary Differential Equation","metrics":{"Accuracy":"99.63","Percentage error":"0.37"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/augmented-neural-odes","paper_url":"https://arxiv.org/abs/1904.01681v3","paper_title":"Augmented Neural ODEs","code":"https://github.com/EmilienDupont/augmented-neural-odes","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":2}},{"rank_in_archive_order":24,"model":"DSN","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2014-09-18","paper":"/paper/deeply-supervised-nets","paper_url":"http://arxiv.org/abs/1409.5185v2","paper_title":"Deeply-Supervised Nets","code":"https://github.com/ellisdg/3DUnetCNN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":21,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"CKN","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2014-06-12","paper":"/paper/convolutional-kernel-networks","paper_url":"http://arxiv.org/abs/1406.3332v2","paper_title":"Convolutional Kernel Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"C-SVDDNet","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2014-12-23","paper":"/paper/unsupervised-feature-learning-with-c-svddnet","paper_url":"http://arxiv.org/abs/1412.7259v3","paper_title":"Unsupervised Feature Learning with C-SVDDNet","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"HOPE","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2015-02-03","paper":"/paper/hybrid-orthogonal-projection-and-estimation","paper_url":"http://arxiv.org/abs/1502.00702v2","paper_title":"Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"FLSCNN","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2015-03-16","paper":"/paper/enhanced-image-classification-with-a-fast","paper_url":"http://arxiv.org/abs/1503.04596v3","paper_title":"Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"MIM","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2015-08-03","paper":"/paper/on-the-importance-of-normalisation-layers-in","paper_url":"http://arxiv.org/abs/1508.00330v2","paper_title":"On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"Fitnet-LSUV-SVM","metrics":{"Percentage error":"0.4"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/all-you-need-is-a-good-init","paper_url":"http://arxiv.org/abs/1511.06422v7","paper_title":"All you need is a good init","code":"https://github.com/ducha-aiki/LSUVinit","n_code_links":11,"syntology":{"n_ran":0,"n_unverified":19,"n_samples":19,"n_pointer_only_licence":2}},{"rank_in_archive_order":31,"model":"TAAF-CNN","metrics":{"Accuracy":"99.52%","Cross Entropy Loss":"0.0188","Epochs":"35","Percentage error":"0.48%","Trainable Parameters":"421642"},"uses_additional_data":false,"paper_date":"2025-02-13","paper":"/paper/evaluating-the-performance-of-taaf-for-image","paper_url":"https://www.academia.edu/127610553/The_Analog_Activation_Function_TAAF_of_Emergent_Linear_Systems_Evaluating_the_Performance_of_The_Analog_Activation_Function_TAAF_on_MNIST_and_CIFAR_10_Datasets","paper_title":"Evaluating the Performance of TAAF for image classification models","code":"https://github.com/bryn-gnolbs/TAAF-for-Image-Classification","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN)","metrics":{"Accuracy":"99.5","Percentage error":"0.5","Trainable Parameters":"1882602"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"Maxout Networks","metrics":{"Percentage error":"0.5"},"uses_additional_data":false,"paper_date":"2013-02-18","paper":"/paper/maxout-networks","paper_url":"http://arxiv.org/abs/1302.4389v4","paper_title":"Maxout Networks","code":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Maxout_Networks","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"NiN","metrics":{"Percentage error":"0.5"},"uses_additional_data":false,"paper_date":"2013-12-16","paper":"/paper/network-in-network","paper_url":"http://arxiv.org/abs/1312.4400v3","paper_title":"Network In Network","code":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Network_In_Network","n_code_links":17,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":35,"model":"ReNet","metrics":{"Percentage error":"0.5"},"uses_additional_data":false,"paper_date":"2015-05-03","paper":"/paper/renet-a-recurrent-neural-network-based","paper_url":"http://arxiv.org/abs/1505.00393v3","paper_title":"ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks","code":"https://github.com/fvisin/reseg","n_code_links":4,"syntology":null},{"rank_in_archive_order":36,"model":"DCNN+GFE","metrics":{"Percentage error":"0.5"},"uses_additional_data":false,"paper_date":"2017-10-06","paper":"/paper/deep-convolutional-neural-networks-as-generic","paper_url":"http://arxiv.org/abs/1710.02286v1","paper_title":"Deep Convolutional Neural Networks as Generic Feature Extractors","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"VDN","metrics":{"Percentage error":"0.5"},"uses_additional_data":false,"paper_date":"2015-07-22","paper":"/paper/training-very-deep-networks","paper_url":"http://arxiv.org/abs/1507.06228v2","paper_title":"Training Very Deep Networks","code":"https://github.com/LiyuanLucasLiu/LM-LSTM-CRF","n_code_links":3,"syntology":null},{"rank_in_archive_order":38,"model":"NeuPDE","metrics":{"Percentage error":"0.51"},"uses_additional_data":false,"paper_date":"2019-08-08","paper":"/paper/neupde-neural-network-based-ordinary-and","paper_url":"https://arxiv.org/abs/1908.03190v1","paper_title":"NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"Simple CNN with BaikalCMA loss","metrics":{"Percentage error":"0.53"},"uses_additional_data":false,"paper_date":"2019-05-27","paper":"/paper/improved-training-speed-accuracy-and-data","paper_url":"https://arxiv.org/abs/1905.11528v3","paper_title":"Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization","code":"https://github.com/sgonzalez/SwiftGenetics","n_code_links":2,"syntology":null},{"rank_in_archive_order":40,"model":"SEER (RegNet10B)","metrics":{"Accuracy":"99.42","Percentage error":"0.58"},"uses_additional_data":false,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"Convolutional Tsetlin Machine","metrics":{"Accuracy":"99.4","Percentage error":"0.6"},"uses_additional_data":false,"paper_date":"2019-05-23","paper":"/paper/the-convolutional-tsetlin-machine","paper_url":"https://arxiv.org/abs/1905.09688v5","paper_title":"The Convolutional Tsetlin Machine","code":"https://github.com/cair/TsetlinMachine","n_code_links":9,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"PCANet","metrics":{"Percentage error":"0.6"},"uses_additional_data":false,"paper_date":"2014-04-14","paper":"/paper/pcanet-a-simple-deep-learning-baseline-for","paper_url":"http://arxiv.org/abs/1404.3606v2","paper_title":"PCANet: A Simple Deep Learning Baseline for Image Classification?","code":"https://github.com/Ldpe2G/PCANet","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"DiffPrune (LeNet5)","metrics":{"Percentage error":"0.6"},"uses_additional_data":false,"paper_date":"2020-12-07","paper":"/paper/diffprune-neural-network-pruning-with","paper_url":"https://arxiv.org/abs/2012.03653v2","paper_title":"DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization","code":"https://bitbucket.org/YanivShu/diffprune_public","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"Deep Fried Convnets","metrics":{"Percentage error":"0.7"},"uses_additional_data":false,"paper_date":"2014-12-22","paper":"/paper/deep-fried-convnets","paper_url":"http://arxiv.org/abs/1412.7149v4","paper_title":"Deep Fried Convnets","code":"https://github.com/v0lta/wavelet-network-compression","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"Sparse Activity and Sparse Connectivity in Supervised Learning","metrics":{"Percentage error":"0.8"},"uses_additional_data":false,"paper_date":"2016-03-28","paper":"/paper/sparse-activity-and-sparse-connectivity-in","paper_url":"http://arxiv.org/abs/1603.08367v1","paper_title":"Sparse Activity and Sparse Connectivity in Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"Explaining and Harnessing Adversarial Examples","metrics":{"Percentage error":"0.8"},"uses_additional_data":false,"paper_date":"2014-12-20","paper":"/paper/explaining-and-harnessing-adversarial","paper_url":"http://arxiv.org/abs/1412.6572v3","paper_title":"Explaining and Harnessing Adversarial Examples","code":"https://github.com/cleverhans-lab/cleverhans","n_code_links":59,"syntology":{"n_ran":10,"n_unverified":11,"n_samples":21,"n_pointer_only_licence":8}},{"rank_in_archive_order":47,"model":"BinaryConnect","metrics":{"Percentage error":"1.0"},"uses_additional_data":false,"paper_date":"2015-11-02","paper":"/paper/binaryconnect-training-deep-neural-networks","paper_url":"http://arxiv.org/abs/1511.00363v3","paper_title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","code":"https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":48,"model":"Convolutional PMM (Parametric Matrix Model)","metrics":{"Accuracy":"98.99","Percentage error":"1.01","Trainable Parameters":"129416"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/parametric-matrix-models","paper_url":"https://arxiv.org/abs/2401.11694v6","paper_title":"Parametric Matrix Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":49,"model":"LeNet 300-100 (Sparse Momentum)","metrics":{"Percentage error":"1.26"},"uses_additional_data":false,"paper_date":"2019-07-10","paper":"/paper/sparse-networks-from-scratch-faster-training","paper_url":"https://arxiv.org/abs/1907.04840v2","paper_title":"Sparse Networks from Scratch: Faster Training without Losing Performance","code":"https://github.com/TimDettmers/sparse_learning","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"Convolutional Clustering","metrics":{"Percentage error":"1.4"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/convolutional-clustering-for-unsupervised","paper_url":"http://arxiv.org/abs/1511.06241v2","paper_title":"Convolutional Clustering for Unsupervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"CNN Model by Som","metrics":{"Accuracy":"98.59","Percentage error":"1.41"},"uses_additional_data":false,"paper_date":"2017-05-08","paper":"/paper/convolutional-sequence-to-sequence-learning","paper_url":"http://arxiv.org/abs/1705.03122v3","paper_title":"Convolutional Sequence to Sequence Learning","code":"https://github.com/facebookresearch/fairseq","n_code_links":37,"syntology":null},{"rank_in_archive_order":52,"model":"Weighted Tsetlin Machine","metrics":{"Accuracy":"98.5","Percentage error":"1.5"},"uses_additional_data":false,"paper_date":"2019-11-28","paper":"/paper/the-weighted-tsetlin-machine-compressed","paper_url":"https://arxiv.org/abs/1911.12607v4","paper_title":"The Weighted Tsetlin Machine: Compressed Representations with Weighted Clauses","code":"https://github.com/cair/pyTsetlinMachine","n_code_links":2,"syntology":null},{"rank_in_archive_order":53,"model":"MLP (ideal number of groups)","metrics":{"Percentage error":"1.67"},"uses_additional_data":false,"paper_date":"2023-02-07","paper":"/paper/on-the-ideal-number-of-groups-for-isometric","paper_url":"https://arxiv.org/abs/2302.03193v1","paper_title":"On the Ideal Number of Groups for Isometric Gradient Propagation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":54,"model":"Perceptron with a tensor train layer","metrics":{"Accuracy":"98.2","Percentage error":"1.8"},"uses_additional_data":false,"paper_date":"2015-09-22","paper":"/paper/tensorizing-neural-networks","paper_url":"http://arxiv.org/abs/1509.06569v2","paper_title":"Tensorizing Neural Networks","code":"https://github.com/timgaripov/TensorNet-TF","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":55,"model":"ANODE","metrics":{"Accuracy":"98.2","Percentage error":"1.8"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/augmented-neural-odes","paper_url":"https://arxiv.org/abs/1904.01681v3","paper_title":"Augmented Neural ODEs","code":"https://github.com/EmilienDupont/augmented-neural-odes","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":2}},{"rank_in_archive_order":56,"model":"Tsetlin Machine","metrics":{"Accuracy":"98.2","Percentage error":"1.8"},"uses_additional_data":false,"paper_date":"2018-04-04","paper":"/paper/the-tsetlin-machine-a-game-theoretic-bandit","paper_url":"http://arxiv.org/abs/1804.01508v10","paper_title":"The Tsetlin Machine - A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic","code":"https://github.com/cair/TsetlinMachine","n_code_links":16,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"GECCO","metrics":{"Accuracy":"98.04","Percentage error":"1.96"},"uses_additional_data":false,"paper_date":"2024-02-01","paper":"/paper/a-single-graph-convolution-is-all-you-need","paper_url":"https://arxiv.org/abs/2402.00564v6","paper_title":"A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification","code":"https://github.com/geccoproject/gecco","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"PMM (Parametric Matrix Model)","metrics":{"Accuracy":"97.38","Percentage error":"2.62","Trainable Parameters":"4990"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/parametric-matrix-models","paper_url":"https://arxiv.org/abs/2401.11694v6","paper_title":"Parametric Matrix Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":59,"model":"DNN-5 (Trainable Activations)","metrics":{"Accuracy":"97.2","Percentage error":"2.8","Trainable Parameters":"575051"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/trainable-activations-for-image","paper_url":"https://doi.org/10.20944/preprints202301.0463.v1","paper_title":"Trainable Activations for Image Classification","code":"https://github.com/Pe4enIks/TrainableActivation","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"DNN-3 (Trainable Activations)","metrics":{"Accuracy":"97.0","Percentage error":"3.0","Trainable Parameters":"386719"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/trainable-activations-for-image","paper_url":"https://doi.org/10.20944/preprints202301.0463.v1","paper_title":"Trainable Activations for Image Classification","code":"https://github.com/Pe4enIks/TrainableActivation","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"DNN-2 (Trainable Activations)","metrics":{"Accuracy":"96.4","Percentage error":"3.6","Trainable Parameters":"311651"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/trainable-activations-for-image","paper_url":"https://doi.org/10.20944/preprints202301.0463.v1","paper_title":"Trainable Activations for Image Classification","code":"https://github.com/Pe4enIks/TrainableActivation","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"Zhao et al. (2015) (auto-encoder)","metrics":{"Percentage error":"4.76"},"uses_additional_data":false,"paper_date":"2015-06-08","paper":"/paper/stacked-what-where-auto-encoders","paper_url":"http://arxiv.org/abs/1506.02351v8","paper_title":"Stacked What-Where Auto-encoders","code":"https://github.com/isaacgerg/keras_odds_and_ends","n_code_links":2,"syntology":null},{"rank_in_archive_order":63,"model":"ProjectionNet","metrics":{"Accuracy":"95.0","Percentage error":"5.0"},"uses_additional_data":false,"paper_date":"2017-08-02","paper":"/paper/projectionnet-learning-efficient-on-device","paper_url":"http://arxiv.org/abs/1708.00630v2","paper_title":"ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":64,"model":"µ2Net (ViT-L/16)","metrics":{"Accuracy":"99.75"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/an-evolutionary-approach-to-dynamic","paper_url":"https://arxiv.org/abs/2205.12755v6","paper_title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","code":"https://github.com/google-research/google-research/tree/master/muNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":65,"model":"MobileNet_XnODR","metrics":{"Accuracy":"99.68"},"uses_additional_data":false,"paper_date":"2021-11-21","paper":"/paper/xnodr-and-xnidr-two-accurate-and-fast-fully","paper_url":"https://arxiv.org/abs/2111.10854v3","paper_title":"XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks","code":"https://github.com/jiansfoggy/CODE-SHOW/tree/master/Python/XnODR_and_XnIDR","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"ResNet-9","metrics":{"Accuracy":"99.68"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/cnn-filter-db-an-empirical-investigation-of","paper_url":"https://arxiv.org/abs/2203.15331v2","paper_title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","code":"https://github.com/paulgavrikov/cnn-filter-db","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"LR-Net","metrics":{"Accuracy":"99.47"},"uses_additional_data":false,"paper_date":"2022-07-19","paper":"/paper/a-block-based-convolutional-neural-network","paper_url":"https://arxiv.org/abs/2207.09531v5","paper_title":"LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification","code":"https://github.com/AshkanGanj/Block-Based-ImageClassification-Architecture","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"CNN+ Wilson-Cowan model RNN","metrics":{"Accuracy":"99.31"},"uses_additional_data":false,"paper_date":"2024-06-24","paper":"/paper/learning-in-wilson-cowan-model-for","paper_url":"https://arxiv.org/abs/2406.16453v2","paper_title":"Learning in Wilson-Cowan model for metapopulation","code":"https://github.com/raffaelemarino/learning_in_wilsoncowan","n_code_links":1,"syntology":null},{"rank_in_archive_order":69,"model":"FastSNN (CNN)","metrics":{"Accuracy":"99.3"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/accelerating-spiking-neural-network-training","paper_url":"https://arxiv.org/abs/2205.15286v2","paper_title":"Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks","code":"https://github.com/webstorms/fastsnn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":70,"model":"rKAN","metrics":{"Accuracy":"99.293"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/rkan-rational-kolmogorov-arnold-networks","paper_url":"https://arxiv.org/abs/2406.14495v1","paper_title":"rKAN: Rational Kolmogorov-Arnold Networks","code":"https://github.com/alirezaafzalaghaei/rkan","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"CNN-5 Layer","metrics":{"Accuracy":"99.27"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/robust-training-in-high-dimensions-via-block","paper_url":"https://arxiv.org/abs/2106.08882v1","paper_title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","code":"https://github.com/anishacharya/BGMD","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"fKAN","metrics":{"Accuracy":"99.228"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/fkan-fractional-kolmogorov-arnold-networks","paper_url":"https://arxiv.org/abs/2406.07456v1","paper_title":"fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions","code":"https://github.com/alirezaafzalaghaei/fKAN","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":73,"model":"StiDi-BP in R-CSNN","metrics":{"Accuracy":"99.2"},"uses_additional_data":false,"paper_date":"2021-08-31","paper":"/paper/spike-time-displacement-based-error","paper_url":"https://arxiv.org/abs/2108.13621v1","paper_title":"Spike time displacement based error backpropagation in convolutional spiking neural networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":74,"model":"Wilson-Cowan model RNN","metrics":{"Accuracy":"98.13"},"uses_additional_data":false,"paper_date":"2024-06-24","paper":"/paper/learning-in-wilson-cowan-model-for","paper_url":"https://arxiv.org/abs/2406.16453v2","paper_title":"Learning in Wilson-Cowan model for metapopulation","code":"https://github.com/raffaelemarino/learning_in_wilsoncowan","n_code_links":1,"syntology":null},{"rank_in_archive_order":75,"model":"Hypervector Tsetlin Machine","metrics":{"Accuracy":"98.13"},"uses_additional_data":false,"paper_date":"2024-06-04","paper":"/paper/exploring-effects-of-hyperdimensional-vectors","paper_url":"https://arxiv.org/abs/2406.02648v1","paper_title":"Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":76,"model":"ViT-Mini_D9","metrics":{"Accuracy":"98.03","Trainable Parameters":"1208586"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"FastSNN (MLP)","metrics":{"Accuracy":"97.91"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/accelerating-spiking-neural-network-training","paper_url":"https://arxiv.org/abs/2205.15286v2","paper_title":"Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks","code":"https://github.com/webstorms/fastsnn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":78,"model":"Binarized MLP with on-chip spiking backpropagation (on Loihi)","metrics":{"Accuracy":"96.2"},"uses_additional_data":false,"paper_date":"2021-06-13","paper":"/paper/the-backpropagation-algorithm-implemented-on","paper_url":"https://arxiv.org/abs/2106.07030v2","paper_title":"The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware","code":"https://github.com/lanl/spikingBackprop","n_code_links":1,"syntology":null},{"rank_in_archive_order":79,"model":"SNNL-5","metrics":{"Accuracy":"95.5"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/improving-k-means-clustering-performance-with","paper_url":"https://arxiv.org/abs/2006.04535v1","paper_title":"Improving k-Means Clustering Performance with Disentangled Internal Representations","code":"https://gitlab.com/afagarap/pt-snnl","n_code_links":1,"syntology":null},{"rank_in_archive_order":80,"model":"pFedBreD_ns_mg","metrics":{"Accuracy":"92.47"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/personalized-federated-learning-with-hidden","paper_url":"https://arxiv.org/abs/2211.10684v2","paper_title":"Personalized Federated Learning with Hidden Information on Personalized Prior","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":81,"model":"DGMMC-S","metrics":{"Top 1 Accuracy":"70"},"uses_additional_data":false,"paper_date":"2024-10-17","paper":"/paper/performance-of-gaussian-mixture-model","paper_url":"https://arxiv.org/abs/2410.13421v1","paper_title":"Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces","code":"https://github.com/cvmlmu/dgmmc","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":25,"rows_with_any_sample_ran":15,"distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":48,"n_unverified":204,"n_samples":252,"n_pointer_only_licence":33,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":50,"n_unverified":213,"n_samples":263,"n_pointer_only_licence":35,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}