{"url":"/sota/image-classification-on-svhn","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"SVHN","url":"/dataset/svhn"},"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","Percentage correct"],"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","Percentage correct":null}},"counts":{"rows":62,"rows_with_code":54,"rows_with_paper_page":58,"rows_dated":58,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"E2E-M3","metrics":{"Percentage error":"1.0"},"uses_additional_data":false,"paper_date":"2020-07-30","paper":"/paper/rethinking-recurrent-neural-networks-and","paper_url":"https://arxiv.org/abs/2007.15161v3","paper_title":"Rethinking Recurrent Neural Networks and Other Improvements for Image Classification","code":"https://github.com/leonlha/e2e-3m","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Wide-ResNet-28-10 (Fast AA)","metrics":{"Percentage error":"1.1"},"uses_additional_data":false,"paper_date":"2019-05-01","paper":"/paper/fast-autoaugment","paper_url":"https://arxiv.org/abs/1905.00397v2","paper_title":"Fast AutoAugment","code":"https://github.com/kakaobrain/fast-autoaugment","n_code_links":11,"syntology":{"n_ran":22,"n_unverified":18,"n_samples":40,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"Colornet","metrics":{"Percentage error":"1.11"},"uses_additional_data":false,"paper_date":"2019-02-01","paper":"/paper/colornet-investigating-the-importance-of","paper_url":"http://arxiv.org/abs/1902.00267v1","paper_title":"ColorNet: Investigating the importance of color spaces for image classification","code":"https://github.com/kini5gowda/ColorNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"PBA [ho2019pba]","metrics":{"Percentage error":"1.2"},"uses_additional_data":false,"paper_date":"2019-05-14","paper":"/paper/190505393","paper_url":"https://arxiv.org/abs/1905.05393v1","paper_title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","code":"https://github.com/arcelien/pba","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":18,"n_samples":18,"n_pointer_only_licence":18}},{"rank_in_archive_order":5,"model":"WaveMixLite-144/15","metrics":{"Percentage error":"1.27"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/wavemix-lite-a-resource-efficient-neural","paper_url":"https://arxiv.org/abs/2205.14375v5","paper_title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Cutout","metrics":{"Percentage error":"1.30"},"uses_additional_data":false,"paper_date":"2017-08-15","paper":"/paper/improved-regularization-of-convolutional","paper_url":"http://arxiv.org/abs/1708.04552v2","paper_title":"Improved Regularization of Convolutional Neural Networks with Cutout","code":"https://github.com/albumentations-team/albumentations","n_code_links":28,"syntology":{"n_ran":21,"n_unverified":3,"n_samples":24,"n_pointer_only_licence":5}},{"rank_in_archive_order":7,"model":"PyramidNet + AA (AMP)","metrics":{"Percentage error":"1.35"},"uses_additional_data":false,"paper_date":"2020-10-10","paper":"/paper/regularizing-neural-networks-via-adversarial","paper_url":"https://arxiv.org/abs/2010.04925v4","paper_title":"Regularizing Neural Networks via Adversarial Model Perturbation","code":"https://github.com/hiyouga/AMP-Regularizer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"WRN + fixup init + mixup + cutout","metrics":{"Percentage error":"1.4"},"uses_additional_data":false,"paper_date":"2019-01-27","paper":"/paper/fixup-initialization-residual-learning","paper_url":"http://arxiv.org/abs/1901.09321v2","paper_title":"Fixup Initialization: Residual Learning Without Normalization","code":"https://github.com/hongyi-zhang/Fixup","n_code_links":10,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":9,"model":"Drop-Activation","metrics":{"Percentage error":"1.46"},"uses_additional_data":false,"paper_date":"2018-11-14","paper":"/paper/drop-activation-implicit-parameter-reduction","paper_url":"https://arxiv.org/abs/1811.05850v5","paper_title":"Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization","code":"https://github.com/LeungSamWai/Drop-Activation","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SOPCNN","metrics":{"Percentage error":"1.50"},"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":11,"model":"EraseReLU","metrics":{"Percentage error":"1.54"},"uses_additional_data":false,"paper_date":"2017-09-22","paper":"/paper/eraserelu-a-simple-way-to-ease-the-training","paper_url":"http://arxiv.org/abs/1709.07634v2","paper_title":"EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Wide Residual Networks","metrics":{"Percentage error":"1.54"},"uses_additional_data":false,"paper_date":"2016-05-23","paper":"/paper/wide-residual-networks","paper_url":"http://arxiv.org/abs/1605.07146v4","paper_title":"Wide Residual Networks","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":72,"syntology":{"n_ran":60,"n_unverified":36,"n_samples":96,"n_pointer_only_licence":46}},{"rank_in_archive_order":13,"model":"CoPaNet-R-164","metrics":{"Percentage error":"1.58"},"uses_additional_data":false,"paper_date":"2017-09-29","paper":"/paper/deep-competitive-pathway-networks","paper_url":"http://arxiv.org/abs/1709.10282v1","paper_title":"Deep Competitive Pathway Networks","code":"https://github.com/JiaRenChang/CoPaNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"WaveMixLite","metrics":{"Percentage error":"1.58"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/wavemix-lite-a-resource-efficient-neural-1","paper_url":"https://openreview.net/forum?id=y_icnxeeUcl","paper_title":"WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis","code":"https://github.com/pranavphoenix/WaveMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"DenseNet","metrics":{"Percentage error":"1.59"},"uses_additional_data":false,"paper_date":"2016-08-25","paper":"/paper/densely-connected-convolutional-networks","paper_url":"http://arxiv.org/abs/1608.06993v5","paper_title":"Densely Connected Convolutional Networks","code":"https://github.com/pytorch/vision","n_code_links":146,"syntology":{"n_ran":18,"n_unverified":53,"n_samples":71,"n_pointer_only_licence":7}},{"rank_in_archive_order":16,"model":"Multilevel Residual Networks","metrics":{"Percentage error":"1.59"},"uses_additional_data":false,"paper_date":"2016-08-09","paper":"/paper/residual-networks-of-residual-networks","paper_url":"http://arxiv.org/abs/1608.02908v2","paper_title":"Residual Networks of Residual Networks: Multilevel Residual Networks","code":"https://github.com/osmr/imgclsmob","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"VGG8B + LocalLearning + CO","metrics":{"Percentage error":"1.65"},"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":18,"model":"Tree+Max-Avg pooling","metrics":{"Percentage error":"1.7"},"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":19,"model":"Wide ResNet","metrics":{"Percentage error":"1.7"},"uses_additional_data":false,"paper_date":"2016-05-23","paper":"/paper/wide-residual-networks","paper_url":"http://arxiv.org/abs/1605.07146v4","paper_title":"Wide Residual Networks","code":"https://github.com/tensorflow/models/tree/master/research/autoaugment","n_code_links":72,"syntology":{"n_ran":60,"n_unverified":36,"n_samples":96,"n_pointer_only_licence":46}},{"rank_in_archive_order":20,"model":"Stochastic Depth","metrics":{"Percentage error":"1.75"},"uses_additional_data":false,"paper_date":"2016-03-30","paper":"/paper/deep-networks-with-stochastic-depth","paper_url":"http://arxiv.org/abs/1603.09382v3","paper_title":"Deep Networks with Stochastic Depth","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":15,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":2}},{"rank_in_archive_order":21,"model":"RCNN-96","metrics":{"Percentage error":"1.8"},"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":22,"model":"BNM NiN","metrics":{"Percentage error":"1.8"},"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":23,"model":"CMsC","metrics":{"Percentage error":"1.8"},"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":24,"model":"Regularization of Neural Networks using DropConnect","metrics":{"Percentage error":"1.9"},"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":25,"model":"DSN","metrics":{"Percentage error":"1.9"},"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":26,"model":"MLR DNN","metrics":{"Percentage error":"1.9"},"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":27,"model":"MIM","metrics":{"Percentage error":"2.0"},"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":28,"model":"FractalNet","metrics":{"Percentage error":"2.01"},"uses_additional_data":false,"paper_date":"2016-05-24","paper":"/paper/fractalnet-ultra-deep-neural-networks-without","paper_url":"http://arxiv.org/abs/1605.07648v4","paper_title":"FractalNet: Ultra-Deep Neural Networks without Residuals","code":"https://github.com/osmr/imgclsmob","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":1}},{"rank_in_archive_order":29,"model":"DCNN","metrics":{"Percentage error":"2.2"},"uses_additional_data":false,"paper_date":"2013-12-20","paper":"/paper/multi-digit-number-recognition-from-street","paper_url":"http://arxiv.org/abs/1312.6082v4","paper_title":"Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks","code":"https://github.com/tianyu-tristan/Visual-Attention-Model","n_code_links":17,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":30,"model":"BinaryConnect","metrics":{"Percentage error":"2.2"},"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":31,"model":"EXACT (WRN-16-8)","metrics":{"Percentage error":"2.21"},"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":32,"model":"EnAET","metrics":{"Percentage error":"2.22"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/enaet-self-trained-ensemble-autoencoding","paper_url":"https://arxiv.org/abs/1911.09265v2","paper_title":"EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations","code":"https://github.com/maple-research-lab/EnAET","n_code_links":2,"syntology":null},{"rank_in_archive_order":33,"model":"PreActResNet18 (AMP)","metrics":{"Percentage error":"2.30"},"uses_additional_data":false,"paper_date":"2020-10-10","paper":"/paper/regularizing-neural-networks-via-adversarial","paper_url":"https://arxiv.org/abs/2010.04925v4","paper_title":"Regularizing Neural Networks via Adversarial Model Perturbation","code":"https://github.com/hiyouga/AMP-Regularizer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"Network in Network","metrics":{"Percentage error":"2.35"},"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":"2.4"},"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":"Maxout","metrics":{"Percentage error":"2.5"},"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":37,"model":"MixMatch","metrics":{"Percentage error":"2.59"},"uses_additional_data":false,"paper_date":"2019-05-06","paper":"/paper/mixmatch-a-holistic-approach-to-semi","paper_url":"https://arxiv.org/abs/1905.02249v2","paper_title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","code":"https://github.com/google-research/mixmatch","n_code_links":30,"syntology":{"n_ran":39,"n_unverified":24,"n_samples":63,"n_pointer_only_licence":32}},{"rank_in_archive_order":38,"model":"ResNet-18","metrics":{"Percentage error":"2.65"},"uses_additional_data":false,"paper_date":"2022-06-27","paper":"/paper/benchopt-reproducible-efficient-and","paper_url":"https://arxiv.org/abs/2206.13424v3","paper_title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","code":"https://github.com/google-deepmind/optax","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"Stochastic Pooling","metrics":{"Percentage error":"2.8"},"uses_additional_data":false,"paper_date":"2013-01-16","paper":"/paper/stochastic-pooling-for-regularization-of-deep","paper_url":"http://arxiv.org/abs/1301.3557v1","paper_title":"Stochastic Pooling for Regularization of Deep Convolutional Neural Networks","code":"https://github.com/szagoruyko/imagine-nn","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"Deep Complex","metrics":{"Percentage error":"3.3"},"uses_additional_data":false,"paper_date":"2017-05-27","paper":"/paper/deep-complex-networks","paper_url":"http://arxiv.org/abs/1705.09792v4","paper_title":"Deep Complex Networks","code":"https://github.com/ChihebTrabelsi/deep_complex_networks","n_code_links":9,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":41,"model":"FLSCNN","metrics":{"Percentage error":"4.0"},"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":42,"model":"Convolutional neural networks applied to house numbers digit classification","metrics":{"Percentage error":"4.9"},"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":43,"model":"CLS-GAN","metrics":{"Percentage error":"5.98"},"uses_additional_data":false,"paper_date":"2017-01-23","paper":"/paper/loss-sensitive-generative-adversarial","paper_url":"http://arxiv.org/abs/1701.06264v6","paper_title":"Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities","code":"https://github.com/guojunq/lsgan","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"Improved GAN","metrics":{"Percentage error":"8.11"},"uses_additional_data":false,"paper_date":"2016-06-10","paper":"/paper/improved-techniques-for-training-gans","paper_url":"http://arxiv.org/abs/1606.03498v1","paper_title":"Improved Techniques for Training GANs","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":46,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"Local Mixup LeNet","metrics":{"Percentage error":"8.20"},"uses_additional_data":false,"paper_date":"2022-01-12","paper":"/paper/preventing-manifold-intrusion-with-locality","paper_url":"https://arxiv.org/abs/2201.04368v1","paper_title":"Preventing Manifold Intrusion with Locality: Local Mixup","code":"https://github.com/raphael-baena/Local-Mixup","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"Sign-symmetry","metrics":{"Percentage error":"10.16"},"uses_additional_data":false,"paper_date":"2015-10-17","paper":"/paper/how-important-is-weight-symmetry-in","paper_url":"http://arxiv.org/abs/1510.05067v4","paper_title":"How Important is Weight Symmetry in Backpropagation?","code":"https://github.com/jsalbert/biotorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":47,"model":"SEER (RegNet10B)","metrics":{"Percentage error":"13.6"},"uses_additional_data":true,"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":48,"model":"ANODE","metrics":{"Percentage error":"16.5"},"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":49,"model":"Skip DGN","metrics":{"Percentage error":"16.61"},"uses_additional_data":false,"paper_date":"2016-02-17","paper":"/paper/auxiliary-deep-generative-models","paper_url":"http://arxiv.org/abs/1602.05473v4","paper_title":"Auxiliary Deep Generative Models","code":"https://github.com/larsmaaloee/auxiliary-deep-generative-models","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"DCGAN","metrics":{"Percentage error":"22.48"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/unsupervised-representation-learning-with-1","paper_url":"http://arxiv.org/abs/1511.06434v2","paper_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","code":"https://github.com/tensorflow/models/blob/master/research/slim/nets/dcgan.py","n_code_links":258,"syntology":{"n_ran":113,"n_unverified":106,"n_samples":219,"n_pointer_only_licence":111}},{"rank_in_archive_order":51,"model":"Auxiliary DGN","metrics":{"Percentage error":"22.86"},"uses_additional_data":false,"paper_date":"2016-02-17","paper":"/paper/auxiliary-deep-generative-models","paper_url":"http://arxiv.org/abs/1602.05473v4","paper_title":"Auxiliary Deep Generative Models","code":"https://github.com/larsmaaloee/auxiliary-deep-generative-models","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":52,"model":"Supervised CNN","metrics":{"Percentage error":"28.87"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/unsupervised-representation-learning-with-1","paper_url":"http://arxiv.org/abs/1511.06434v2","paper_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","code":"https://github.com/tensorflow/models/blob/master/research/slim/nets/dcgan.py","n_code_links":258,"syntology":{"n_ran":113,"n_unverified":106,"n_samples":219,"n_pointer_only_licence":111}},{"rank_in_archive_order":53,"model":"M1+M2","metrics":{"Percentage error":"36.02"},"uses_additional_data":false,"paper_date":"2014-06-20","paper":"/paper/semi-supervised-learning-with-deep-generative-1","paper_url":"http://arxiv.org/abs/1406.5298v2","paper_title":"Semi-Supervised Learning with Deep Generative Models","code":"https://github.com/probtorch/probtorch","n_code_links":18,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"DGN","metrics":{"Percentage error":"36.02"},"uses_additional_data":false,"paper_date":"2014-06-20","paper":"/paper/semi-supervised-learning-with-deep-generative-1","paper_url":"http://arxiv.org/abs/1406.5298v2","paper_title":"Semi-Supervised Learning with Deep Generative Models","code":"https://github.com/probtorch/probtorch","n_code_links":18,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":55,"model":"M1+TSVM","metrics":{"Percentage error":"54.33"},"uses_additional_data":false,"paper_date":"2014-06-20","paper":"/paper/semi-supervised-learning-with-deep-generative-1","paper_url":"http://arxiv.org/abs/1406.5298v2","paper_title":"Semi-Supervised Learning with Deep Generative Models","code":"https://github.com/probtorch/probtorch","n_code_links":18,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"M1+KNN","metrics":{"Percentage error":"65.63"},"uses_additional_data":false,"paper_date":"2014-06-20","paper":"/paper/semi-supervised-learning-with-deep-generative-1","paper_url":"http://arxiv.org/abs/1406.5298v2","paper_title":"Semi-Supervised Learning with Deep Generative Models","code":"https://github.com/probtorch/probtorch","n_code_links":18,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"TSVM","metrics":{"Percentage error":"66.55"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/unsupervised-representation-learning-with-1","paper_url":"http://arxiv.org/abs/1511.06434v2","paper_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","code":"https://github.com/tensorflow/models/blob/master/research/slim/nets/dcgan.py","n_code_links":258,"syntology":{"n_ran":113,"n_unverified":106,"n_samples":219,"n_pointer_only_licence":111}},{"rank_in_archive_order":58,"model":"KNN","metrics":{"Percentage error":"77.93"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/unsupervised-representation-learning-with-1","paper_url":"http://arxiv.org/abs/1511.06434v2","paper_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","code":"https://github.com/tensorflow/models/blob/master/research/slim/nets/dcgan.py","n_code_links":258,"syntology":{"n_ran":113,"n_unverified":106,"n_samples":219,"n_pointer_only_licence":111}},{"rank_in_archive_order":59,"model":"Wide-ResNet-28-10","metrics":{"Percentage correct":"98.15"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/automatic-data-augmentation-via-invariance","paper_url":"https://arxiv.org/abs/2209.15031v2","paper_title":"Automatic Data Augmentation via Invariance-Constrained Learning","code":"https://github.com/ihounie/daug","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":60,"model":"ShortNet2-43","metrics":{"Percentage correct":"94.52"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/connection-reduction-is-all-you-need","paper_url":"https://arxiv.org/abs/2208.01424v3","paper_title":"Connection Reduction of DenseNet for Image Recognition","code":"https://github.com/ruiyangju/connection_reduction","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"TripleNet-B","metrics":{"Percentage correct":"94.33"},"uses_additional_data":false,"paper_date":"2022-04-02","paper":"/paper/triplenet-a-low-computing-power-platform-of","paper_url":"https://arxiv.org/abs/2204.00943v4","paper_title":"Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification","code":"https://github.com/RuiyangJu/TripleNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":62,"model":"ThreshNet79","metrics":{"Percentage correct":"94.32"},"uses_additional_data":false,"paper_date":"2022-01-09","paper":"/paper/threshnet-an-efficient-densenet-using","paper_url":"https://arxiv.org/abs/2201.03013v2","paper_title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","code":"https://github.com/ruiyangju/threshnet","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":36,"rows_with_any_sample_ran":23,"distinct_papers_with_graph_line":27,"distinct_papers_with_any_sample_ran":19,"samples_over_distinct_papers":{"n_ran":305,"n_unverified":362,"n_samples":667,"n_pointer_only_licence":244,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":704,"n_unverified":755,"n_samples":1459,"n_pointer_only_licence":623,"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"}}}