{"url":"/sota/semi-supervised-image-classification-on-cifar","task":{"name":"Semi-Supervised Image Classification","url":"/task/semi-supervised-image-classification","note":null},"dataset":{"name":"CIFAR-10, 4000 Labels","url":"/dataset/cifar-10"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.\r\n\r\nYou may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:\r\n\r\n- [An overview of proxy-label approaches for semi-supervised learning](https://ruder.io/semi-supervised/) - Sebastian Ruder\r\n- [Semi-Supervised Learning in Computer Vision](https://amitness.com/2020/07/semi-supervised-learning/) - Amit Chaudhary\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Self-Supervised Semi-Supervised Learning](https://arxiv.org/pdf/1905.03670v2.pdf) )</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"],"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"}},"counts":{"rows":49,"rows_with_code":39,"rows_with_paper_page":48,"rows_dated":48,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Semi-SST (ViT-Small)","metrics":{"Percentage error":"1.41±0.10"},"uses_additional_data":false,"paper_date":"2025-05-31","paper":"/paper/sst-self-training-with-self-adaptive-1","paper_url":"https://arxiv.org/abs/2506.00467v1","paper_title":"SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Super-SST (ViT-Small)","metrics":{"Percentage error":"1.61±0.18"},"uses_additional_data":false,"paper_date":"2025-05-31","paper":"/paper/sst-self-training-with-self-adaptive-1","paper_url":"https://arxiv.org/abs/2506.00467v1","paper_title":"SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Diff-SySC","metrics":{"Percentage error":"3.26±0.06"},"uses_additional_data":false,"paper_date":"2025-02-25","paper":"/paper/diff-sysc-an-approach-using-diffusion-models","paper_url":"https://www.scitepress.org/PublicationsDetail.aspx?ID=8MzrzMi7kMs%3d&t=1","paper_title":"Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"SemCo (μ=7)","metrics":{"Percentage error":"3.8±0.08"},"uses_additional_data":false,"paper_date":"2021-04-12","paper":"/paper/all-labels-are-not-created-equal-enhancing","paper_url":"https://arxiv.org/abs/2104.05248v1","paper_title":"All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training","code":"https://github.com/islam-nassar/semco","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Meta Pseudo Labels (WRN-28-2)","metrics":{"Percentage error":"3.89± 0.07"},"uses_additional_data":false,"paper_date":"2020-03-23","paper":"/paper/meta-pseudo-labels","paper_url":"https://arxiv.org/abs/2003.10580v4","paper_title":"Meta Pseudo Labels","code":"https://github.com/google-research/google-research/tree/master/meta_pseudo_labels","n_code_links":9,"syntology":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"SimMatch","metrics":{"Percentage error":"3.96"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/simmatch-semi-supervised-learning-with","paper_url":"https://arxiv.org/abs/2203.06915v2","paper_title":"SimMatch: Semi-supervised Learning with Similarity Matching","code":"https://github.com/kylezheng1997/simmatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"PAWS-NN (WRN-28-2)","metrics":{"Percentage error":"4.0 ± 0.25"},"uses_additional_data":false,"paper_date":"2021-04-28","paper":"/paper/semi-supervised-learning-of-visual-features","paper_url":"https://arxiv.org/abs/2104.13963v3","paper_title":"Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples","code":"https://github.com/facebookresearch/suncet","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":14,"n_samples":21,"n_pointer_only_licence":3}},{"rank_in_archive_order":8,"model":"SelfMatch","metrics":{"Percentage error":"4.06±0.08"},"uses_additional_data":false,"paper_date":"2021-01-16","paper":"/paper/selfmatch-combining-contrastive-self","paper_url":"https://arxiv.org/abs/2101.06480v1","paper_title":"SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Dash (RA, ours)","metrics":{"Percentage error":"4.08±0.06"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/dash-semi-supervised-learning-with-dynamic","paper_url":"https://arxiv.org/abs/2109.00650v1","paper_title":"Dash: Semi-Supervised Learning with Dynamic Thresholding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Self Meta Pseudo Labels","metrics":{"Percentage error":"4.09"},"uses_additional_data":false,"paper_date":"2022-12-27","paper":"/paper/self-meta-pseudo-labels-meta-pseudo-labels","paper_url":"https://arxiv.org/abs/2212.13420v1","paper_title":"Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"NP-Match","metrics":{"Percentage error":"4.11±0.02"},"uses_additional_data":false,"paper_date":"2022-07-03","paper":"/paper/np-match-when-neural-processes-meet-semi","paper_url":"https://arxiv.org/abs/2207.01066v1","paper_title":"NP-Match: When Neural Processes meet Semi-Supervised Learning","code":"https://github.com/jianf-wang/np-match","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"FixMatch+DM","metrics":{"Percentage error":"4.13±0.11"},"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":13,"model":"FixMatch+CR","metrics":{"Percentage error":"4.16"},"uses_additional_data":false,"paper_date":"2022-01-17","paper":"/paper/contrastive-regularization-for-semi","paper_url":"https://arxiv.org/abs/2201.06247v2","paper_title":"Contrastive Regularization for Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"EnAET","metrics":{"Percentage error":"4.18"},"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":15,"model":"FlexMatch","metrics":{"Percentage error":"4.19±0.01"},"uses_additional_data":false,"paper_date":"2021-10-15","paper":"/paper/flexmatch-boosting-semi-supervised-learning","paper_url":"https://arxiv.org/abs/2110.08263v3","paper_title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","code":"https://github.com/torchssl/torchssl","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"DP-SSL","metrics":{"Percentage error":"4.23±0.20"},"uses_additional_data":false,"paper_date":"2021-10-26","paper":"/paper/dp-ssl-towards-robust-semi-supervised","paper_url":"https://arxiv.org/abs/2110.13740v1","paper_title":"DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"UPS (wrn-28-2)","metrics":{"Percentage error":"4.25"},"uses_additional_data":false,"paper_date":"2022-07-03","paper":"/paper/np-match-when-neural-processes-meet-semi","paper_url":"https://arxiv.org/abs/2207.01066v1","paper_title":"NP-Match: When Neural Processes meet Semi-Supervised Learning","code":"https://github.com/jianf-wang/np-match","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"FixMatch (CTA)","metrics":{"Percentage error":"4.31"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning","paper_url":"https://arxiv.org/abs/2001.07685v2","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":26,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":19,"model":"LaplaceNet (WRN-28-2)","metrics":{"Percentage error":"4.35±0.10"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/laplacenet-a-hybrid-energy-neural-model-for","paper_url":"https://arxiv.org/abs/2106.04527v3","paper_title":"LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification","code":"https://github.com/psellcam/LaplaceNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DoubleMatch","metrics":{"Percentage error":"4.65±0.17"},"uses_additional_data":false,"paper_date":"2022-05-11","paper":"/paper/doublematch-improving-semi-supervised","paper_url":"https://arxiv.org/abs/2205.05575v1","paper_title":"DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision","code":"https://github.com/walline/doublematch","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"UPS (Shake-Shake)","metrics":{"Percentage error":"4.86"},"uses_additional_data":false,"paper_date":"2021-01-15","paper":"/paper/in-defense-of-pseudo-labeling-an-uncertainty-1","paper_url":"https://arxiv.org/abs/2101.06329v3","paper_title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","code":"https://github.com/nayeemrizve/ups","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":22,"model":"LaplaceNet (CNN-13)","metrics":{"Percentage error":"4.99±0.08"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/laplacenet-a-hybrid-energy-neural-model-for","paper_url":"https://arxiv.org/abs/2106.04527v3","paper_title":"LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification","code":"https://github.com/psellcam/LaplaceNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"SWSA","metrics":{"Percentage error":"5"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/there-are-many-consistent-explanations-of","paper_url":"http://arxiv.org/abs/1806.05594v3","paper_title":"There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average","code":"https://github.com/benathi/fastswa-semi-sup","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"ReMixMatch","metrics":{"Percentage error":"5.14"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/remixmatch-semi-supervised-learning-with-1","paper_url":"https://arxiv.org/abs/1911.09785v2","paper_title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","code":"https://github.com/google-research/mixmatch","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"UDA","metrics":{"Percentage error":"5.27"},"uses_additional_data":false,"paper_date":"2019-04-29","paper":"/paper/unsupervised-data-augmentation-1","paper_url":"https://arxiv.org/abs/1904.12848v6","paper_title":"Unsupervised Data Augmentation for Consistency Training","code":"https://github.com/google-research/uda","n_code_links":20,"syntology":{"n_ran":15,"n_unverified":37,"n_samples":52,"n_pointer_only_licence":9}},{"rank_in_archive_order":26,"model":"R2-D2 (Shake-Shake)","metrics":{"Percentage error":"5.72"},"uses_additional_data":false,"paper_date":"2019-08-09","paper":"/paper/repetitive-reprediction-deep-decipher-for","paper_url":"https://arxiv.org/abs/1908.04345v2","paper_title":"Repetitive Reprediction Deep Decipher for Semi-Supervised Learning","code":"https://github.com/DoctorKey/R2D2.pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"DMT (WRN-28-2)","metrics":{"Percentage error":"5.79"},"uses_additional_data":false,"paper_date":"2020-04-18","paper":"/paper/semi-supervised-semantic-segmentation-via","paper_url":"https://arxiv.org/abs/2004.08514v4","paper_title":"DMT: Dynamic Mutual Training for Semi-Supervised Learning","code":"https://github.com/voldemortX/DST-CBC","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"Adaboost","metrics":{"Percentage error":"6.05±0.12"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/adaptive-boosting-for-domain-adaptation","paper_url":"https://arxiv.org/abs/2103.15685v3","paper_title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","code":"https://github.com/layumi/AdaBoost_Seg","n_code_links":2,"syntology":null},{"rank_in_archive_order":29,"model":"SHOT-VAE","metrics":{"Percentage error":"6.11"},"uses_additional_data":false,"paper_date":"2020-11-21","paper":"/paper/shot-vae-semi-supervised-deep-generative","paper_url":"https://arxiv.org/abs/2011.10684v4","paper_title":"SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations","code":"https://github.com/FengHZ/AAAI2021-260","n_code_links":3,"syntology":null},{"rank_in_archive_order":30,"model":"MixMatch","metrics":{"Percentage error":"6.24"},"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":31,"model":"Mean Teacher","metrics":{"Percentage error":"6.28"},"uses_additional_data":false,"paper_date":"2017-03-06","paper":"/paper/mean-teachers-are-better-role-models-weight","paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","code":"https://github.com/CuriousAI/mean-teacher","n_code_links":8,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":32,"model":"RealMix","metrics":{"Percentage error":"6.38"},"uses_additional_data":false,"paper_date":"2019-12-18","paper":"/paper/realmix-towards-realistic-semi-supervised","paper_url":"https://arxiv.org/abs/1912.08766v1","paper_title":"RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms","code":"https://github.com/uizard-technologies/realmix","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"UPS (CNN-13)","metrics":{"Percentage error":"6.39±0.02"},"uses_additional_data":false,"paper_date":"2021-01-15","paper":"/paper/in-defense-of-pseudo-labeling-an-uncertainty-1","paper_url":"https://arxiv.org/abs/2101.06329v3","paper_title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","code":"https://github.com/nayeemrizve/ups","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":34,"model":"Triple-GAN-V2 (ResNet-26)","metrics":{"Percentage error":"6.54"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/triple-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1912.09784v2","paper_title":"Triple Generative Adversarial Networks","code":"https://github.com/taufikxu/Triple-GAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"ICT (CNN-13)","metrics":{"Percentage error":"7.29"},"uses_additional_data":false,"paper_date":"2019-03-09","paper":"/paper/interpolation-consistency-training-for-semi","paper_url":"https://arxiv.org/abs/1903.03825v5","paper_title":"Interpolation Consistency Training for Semi-Supervised Learning","code":"https://github.com/vikasverma1077/ICT","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":36,"model":"LiDAM","metrics":{"Percentage error":"7.48"},"uses_additional_data":false,"paper_date":"2020-10-13","paper":"/paper/lidam-semi-supervised-learning-with-localized","paper_url":"https://arxiv.org/abs/2010.06668v2","paper_title":"LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"ICT (WRN-28-2)","metrics":{"Percentage error":"7.66"},"uses_additional_data":false,"paper_date":"2019-03-09","paper":"/paper/interpolation-consistency-training-for-semi","paper_url":"https://arxiv.org/abs/1903.03825v5","paper_title":"Interpolation Consistency Training for Semi-Supervised Learning","code":"https://github.com/vikasverma1077/ICT","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":38,"model":"ADA-Net (ConvNet)","metrics":{"Percentage error":"8.72"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/semi-supervised-learning-by-augmented","paper_url":"https://arxiv.org/abs/1905.08171v2","paper_title":"Semi-Supervised Learning by Augmented Distribution Alignment","code":"https://github.com/qinenergy/adanet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"Dual Student (600)","metrics":{"Percentage error":"8.89"},"uses_additional_data":false,"paper_date":"2019-09-03","paper":"/paper/dual-student-breaking-the-limits-of-the","paper_url":"https://arxiv.org/abs/1909.01804v1","paper_title":"Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning","code":"https://github.com/ZHKKKe/DualStudent","n_code_links":2,"syntology":null},{"rank_in_archive_order":40,"model":"Triple-GAN-V2 (CNN-13)","metrics":{"Percentage error":"10.01"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/triple-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1912.09784v2","paper_title":"Triple Generative Adversarial Networks","code":"https://github.com/taufikxu/Triple-GAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"VAT+EntMin","metrics":{"Percentage error":"10.55"},"uses_additional_data":false,"paper_date":"2017-04-13","paper":"/paper/virtual-adversarial-training-a-regularization","paper_url":"http://arxiv.org/abs/1704.03976v2","paper_title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","code":"https://github.com/tensorflow/neural-structured-learning","n_code_links":14,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":11}},{"rank_in_archive_order":42,"model":"GLOT-DR","metrics":{"Percentage error":"10.6"},"uses_additional_data":false,"paper_date":"2022-03-01","paper":"/paper/global-local-regularization-via","paper_url":"https://arxiv.org/abs/2203.00553v3","paper_title":"Global-Local Regularization Via Distributional Robustness","code":"https://github.com/viethoang1512/glot","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"VAT","metrics":{"Percentage error":"11.36"},"uses_additional_data":false,"paper_date":"2017-04-13","paper":"/paper/virtual-adversarial-training-a-regularization","paper_url":"http://arxiv.org/abs/1704.03976v2","paper_title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","code":"https://github.com/tensorflow/neural-structured-learning","n_code_links":14,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":11}},{"rank_in_archive_order":44,"model":"SESEMI SSL (ConvNet)","metrics":{"Percentage error":"11.65"},"uses_additional_data":false,"paper_date":"2019-06-25","paper":"/paper/semi-supervised-learning-with-self-supervised","paper_url":"https://arxiv.org/abs/1906.10343v2","paper_title":"Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning","code":"https://github.com/vuptran/sesemi","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"Pi Model","metrics":{"Percentage error":"12.16"},"uses_additional_data":false,"paper_date":"2016-10-07","paper":"/paper/temporal-ensembling-for-semi-supervised","paper_url":"http://arxiv.org/abs/1610.02242v3","paper_title":"Temporal Ensembling for Semi-Supervised Learning","code":"https://github.com/benathi/fastswa-semi-sup","n_code_links":7,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":2}},{"rank_in_archive_order":46,"model":"Triple-GAN-V2 (CNN-13, no aug)","metrics":{"Percentage error":"12.41"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/triple-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1912.09784v2","paper_title":"Triple Generative Adversarial Networks","code":"https://github.com/taufikxu/Triple-GAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"Bad GAN","metrics":{"Percentage error":"14.41"},"uses_additional_data":false,"paper_date":"2017-05-27","paper":"/paper/good-semi-supervised-learning-that-requires-a","paper_url":"http://arxiv.org/abs/1705.09783v3","paper_title":"Good Semi-supervised Learning that Requires a Bad GAN","code":"https://github.com/kimiyoung/ssl_bad_gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"GAN","metrics":{"Percentage error":"15.59"},"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":49,"model":"Γ-model","metrics":{"Percentage error":"20.4"},"uses_additional_data":false,"paper_date":"2015-07-09","paper":"/paper/semi-supervised-learning-with-ladder-networks","paper_url":"http://arxiv.org/abs/1507.02672v2","paper_title":"Semi-Supervised Learning with Ladder Networks","code":"https://github.com/arasmus/ladder","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}}],"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":17,"distinct_papers_with_graph_line":19,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":145,"n_unverified":143,"n_samples":288,"n_pointer_only_licence":84,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":158,"n_unverified":167,"n_samples":325,"n_pointer_only_licence":101,"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"}}}