{"url":"/sota/image-classification-on-emnist-balanced","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"EMNIST-Balanced","url":"/dataset/emnist"},"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":["Accuracy","Trainable Parameters","NMI"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","Trainable Parameters":null,"NMI":null}},"counts":{"rows":20,"rows_with_code":13,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"EMNIST-mobile","metrics":{"Accuracy":"91.48","Trainable Parameters":" 2250000"},"uses_additional_data":false,"paper_date":"2025-02-08","paper":"/paper/efficient-global-neural-architecture-search","paper_url":"https://arxiv.org/abs/2502.03553","paper_title":"Efficient Global Neural Architecture Search","code":"https://github.com/siddikui/Efficient-Macro-Micro-NAS","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"EMNIST-Tiny","metrics":{"Accuracy":"91.20","Trainable Parameters":"400000"},"uses_additional_data":false,"paper_date":"2025-02-08","paper":"/paper/efficient-global-neural-architecture-search","paper_url":"https://arxiv.org/abs/2502.03553","paper_title":"Efficient Global Neural Architecture Search","code":"https://github.com/siddikui/Efficient-Macro-Micro-NAS","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"WaveMixLite-128/7","metrics":{"Accuracy":"91.06"},"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":4,"model":"VGG-5(Spinal FC)","metrics":{"Accuracy":"91.05","Trainable Parameters":"3630000"},"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":5,"model":"VGG-5","metrics":{"Accuracy":"91.04","Trainable Parameters":"3646000"},"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":6,"model":"TextCaps","metrics":{"Accuracy":"90.46"},"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":7,"model":"OnDev-LCT-8/1","metrics":{"Accuracy":"89.55","Trainable Parameters":"913296"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/ondev-lct-on-device-lightweight-convolutional","paper_url":"https://arxiv.org/abs/2401.11652v1","paper_title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"OnDev-LCT-1/1","metrics":{"Accuracy":"89.52","Trainable Parameters":"216208"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/ondev-lct-on-device-lightweight-convolutional","paper_url":"https://arxiv.org/abs/2401.11652v1","paper_title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"OnDev-LCT-4/1","metrics":{"Accuracy":"89.39","Trainable Parameters":"514960"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/ondev-lct-on-device-lightweight-convolutional","paper_url":"https://arxiv.org/abs/2401.11652v1","paper_title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"OnDev-LCT-2/1","metrics":{"Accuracy":"89.18","Trainable Parameters":"315792"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/ondev-lct-on-device-lightweight-convolutional","paper_url":"https://arxiv.org/abs/2401.11652v1","paper_title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"OptConv+Log+Perc","metrics":{"Accuracy":"87.69"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/efficient-neural-vision-systems-based-on","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Pad_Efficient_Neural_Vision_Systems_Based_on_Convolutional_Image_Acquisition_CVPR_2020_paper.html","paper_title":"Efficient Neural Vision Systems Based on Convolutional Image Acquisition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Convolutional PMM (Parametric Matrix Model)","metrics":{"Accuracy":"85.95","Trainable Parameters":"349172"},"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":13,"model":"HM2-BP","metrics":{"Accuracy":"85.57","Trainable Parameters":"665647"},"uses_additional_data":false,"paper_date":"2018-05-21","paper":"/paper/hybrid-macromicro-level-backpropagation-for","paper_url":"http://arxiv.org/abs/1805.07866v6","paper_title":"Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks","code":"https://github.com/jinyyy666/mm-bp-snn","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"CNN(Spinal FC)","metrics":{"Accuracy":"83.21","Trainable Parameters":"16050"},"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":"CNN(Spinal FC)","metrics":{"Accuracy":"82.77","Trainable Parameters":"13820"},"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":16,"model":"PMM (Parametric Matrix Model)","metrics":{"Accuracy":"81.57","Trainable Parameters":"13792"},"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":17,"model":"CNN","metrics":{"Accuracy":"79.61","Trainable Parameters":"21840"},"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":18,"model":"OPIUM Classifier","metrics":{"Accuracy":"78.94"},"uses_additional_data":false,"paper_date":"2017-02-17","paper":"/paper/emnist-an-extension-of-mnist-to-handwritten","paper_url":"http://arxiv.org/abs/1702.05373v2","paper_title":"EMNIST: an extension of MNIST to handwritten letters","code":"https://github.com/Chizuchizu/amplify-hackathon","n_code_links":31,"syntology":{"n_ran":1,"n_unverified":13,"n_samples":14,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"SNNL-5","metrics":{"Accuracy":"78.5","NMI":"77.6"},"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":20,"model":"Linear Classifier","metrics":{"Accuracy":"50.93"},"uses_additional_data":false,"paper_date":"2017-02-17","paper":"/paper/emnist-an-extension-of-mnist-to-handwritten","paper_url":"http://arxiv.org/abs/1702.05373v2","paper_title":"EMNIST: an extension of MNIST to handwritten letters","code":"https://github.com/Chizuchizu/amplify-hackathon","n_code_links":31,"syntology":{"n_ran":1,"n_unverified":13,"n_samples":14,"n_pointer_only_licence":1}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":113,"n_samples":132,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":126,"n_samples":146,"n_pointer_only_licence":14,"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"}}}