{"url":"/sota/image-classification-on-stl-10","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"STL-10","url":"/dataset/stl-10"},"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 correct","FLOPS","PARAMS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Percentage correct":null,"FLOPS":"lower","PARAMS":"lower"}},"counts":{"rows":117,"rows_with_code":66,"rows_with_paper_page":117,"rows_dated":117,"rows_using_additional_data":18},"rows":[{"rank_in_archive_order":1,"model":"µ2Net+ (ViT-L/16)","metrics":{"Percentage correct":"99.64"},"uses_additional_data":true,"paper_date":"2022-09-15","paper":"/paper/a-continual-development-methodology-for-large","paper_url":"https://arxiv.org/abs/2209.07326v3","paper_title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","code":"https://github.com/google-research/google-research/tree/master/muNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"kNN-CLIP","metrics":{"Percentage correct":"99.6"},"uses_additional_data":true,"paper_date":"2022-04-03","paper":"/paper/revisiting-a-knn-based-image-classification","paper_url":"https://arxiv.org/abs/2204.01186v2","paper_title":"Revisiting a kNN-based Image Classification System with High-capacity Storage","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Wide-ResNet-101 (Spinal FC)","metrics":{"Percentage correct":"98.66"},"uses_additional_data":true,"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":4,"model":"CN(d=128)","metrics":{"Percentage correct":"98.45"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"CN(d=64)","metrics":{"Percentage correct":"98.36"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"NSRL+CN(d=128)","metrics":{"Percentage correct":"98.36"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"NSRL+CN(d=32)","metrics":{"Percentage correct":"98.34"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"NSRL+CN(d=64)","metrics":{"Percentage correct":"98.24"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"CN(d=32)","metrics":{"Percentage correct":"98.17"},"uses_additional_data":true,"paper_date":"2021-01-01","paper":"/paper/toward-understanding-supervised","paper_url":"https://openreview.net/forum?id=lFSZySpXXX8","paper_title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"NAT-M4","metrics":{"FLOPS":"573M","PARAMS":"7.5M","Percentage correct":"97.9"},"uses_additional_data":true,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"NAT-M3","metrics":{"FLOPS":"436M","PARAMS":"7.5M","Percentage correct":"97.8"},"uses_additional_data":true,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"SEER (RegNet10B)","metrics":{"PARAMS":"10000M","Percentage correct":"97.3"},"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":13,"model":"NAT-M2","metrics":{"FLOPS":"303M","PARAMS":"5.1M","Percentage correct":"97.2"},"uses_additional_data":true,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":14,"model":"iGPT-L","metrics":{"Percentage correct":"97.1"},"uses_additional_data":true,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":15,"model":"NAT-M1","metrics":{"FLOPS":"240M","PARAMS":"4.4M","Percentage correct":"96.7"},"uses_additional_data":true,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"EnAET","metrics":{"Percentage correct":"95.48"},"uses_additional_data":true,"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":17,"model":"VGG-19bn","metrics":{"Percentage correct":"95.44"},"uses_additional_data":true,"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":"Diffusion Classifier (zero-shot)","metrics":{"Percentage correct":"95.4"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","paper_url":"https://arxiv.org/abs/2303.16203v3","paper_title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","code":"https://github.com/diffusion-classifier/diffusion-classifier","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"FixMatch (CTA)","metrics":{"Percentage correct":"94.83"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":20,"model":"ReMixMatch","metrics":{"Percentage correct":"94.77"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":21,"model":"AMDIM","metrics":{"Percentage correct":"94.5"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600910","paper_url":"https://arxiv.org/abs/1906.00910v2","paper_title":"Learning Representations by Maximizing Mutual Information Across Views","code":"https://github.com/philip-bachman/amdim-public","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":22,"model":"MixMatch","metrics":{"Percentage correct":"94.41"},"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":23,"model":"AMDIM-L","metrics":{"Percentage correct":"94.2"},"uses_additional_data":true,"paper_date":"2020-07-17","paper":"/paper/generative-pretraining-from-pixels","paper_url":"https://openai.com/blog/image-gpt/","paper_title":"Generative Pretraining from Pixels","code":"https://github.com/openai/image-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":24,"model":"ReMixMatch (K=4)","metrics":{"Percentage correct":"93.82"},"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":"AMDIM","metrics":{"Percentage correct":"93.80"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/a-framework-for-contrastive-self-supervised","paper_url":"https://arxiv.org/abs/2009.00104v1","paper_title":"A Framework For Contrastive Self-Supervised Learning And Designing A New Approach","code":"https://github.com/PyTorchLightning/pytorch-lightning","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"ReMixMatch (K=1)","metrics":{"Percentage correct":"93.23"},"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":27,"model":"MP*","metrics":{"Percentage correct":"93.19"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/increasing-trustworthiness-of-deep-neural","paper_url":"https://arxiv.org/abs/2007.01472v1","paper_title":"Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"UDA","metrics":{"Percentage correct":"92.34"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":29,"model":"YADIM","metrics":{"Percentage correct":"92.15"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/a-framework-for-contrastive-self-supervised","paper_url":"https://arxiv.org/abs/2009.00104v1","paper_title":"A Framework For Contrastive Self-Supervised Learning And Designing A New Approach","code":"https://github.com/PyTorchLightning/pytorch-lightning","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"FixMatch (RA)","metrics":{"Percentage correct":"92.02"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":31,"model":"NSGANetV2","metrics":{"Percentage correct":"92.0"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/nsganetv2-evolutionary-multi-objective","paper_url":"https://arxiv.org/abs/2007.10396v1","paper_title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","code":"https://github.com/mikelzc1990/nsganetv2","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"SESN","metrics":{"Percentage correct":"91.49"},"uses_additional_data":false,"paper_date":"2019-10-14","paper":"/paper/scale-equivariant-steerable-networks-1","paper_url":"https://arxiv.org/abs/1910.11093v2","paper_title":"Scale-Equivariant Steerable Networks","code":"https://github.com/isosnovik/sesn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"Harmonic WRN-16-8","metrics":{"Percentage correct":"90.45"},"uses_additional_data":false,"paper_date":"2019-04-30","paper":"/paper/harmonic-networks-with-limited-training","paper_url":"http://arxiv.org/abs/1905.00135v1","paper_title":"Harmonic Networks with Limited Training Samples","code":"https://github.com/matej-ulicny/harmonic-networks","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"wrn16/8 D8 D4 D1","metrics":{"Percentage correct":"90.20"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/general-e2-equivariant-steerable-cnns-1","paper_url":"https://arxiv.org/abs/1911.08251v2","paper_title":"General $E(2)$-Equivariant Steerable CNNs","code":"https://github.com/QUVA-Lab/e2cnn","n_code_links":7,"syntology":null},{"rank_in_archive_order":35,"model":"DLME (ResNet-50, linear)","metrics":{"Percentage correct":"90.1"},"uses_additional_data":false,"paper_date":"2022-07-07","paper":"/paper/dlme-deep-local-flatness-manifold-embedding","paper_url":"https://arxiv.org/abs/2207.03160v2","paper_title":"DLME: Deep Local-flatness Manifold Embedding","code":"https://github.com/Westlake-AI/openmixup","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"MixMatch","metrics":{"Percentage correct":"89.82"},"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":37,"model":"MixMatch","metrics":{"Percentage correct":"89.59"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":38,"model":"wrn16/8* D8 D4 D1","metrics":{"Percentage correct":"89.43"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/general-e2-equivariant-steerable-cnns-1","paper_url":"https://arxiv.org/abs/1911.08251v2","paper_title":"General $E(2)$-Equivariant Steerable CNNs","code":"https://github.com/QUVA-Lab/e2cnn","n_code_links":7,"syntology":null},{"rank_in_archive_order":39,"model":"wrn16/8* D1 D1 D1","metrics":{"Percentage correct":"88.95"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/general-e2-equivariant-steerable-cnns-1","paper_url":"https://arxiv.org/abs/1911.08251v2","paper_title":"General $E(2)$-Equivariant Steerable CNNs","code":"https://github.com/QUVA-Lab/e2cnn","n_code_links":7,"syntology":null},{"rank_in_archive_order":40,"model":"wrn16/8 D1 D1 D1","metrics":{"Percentage correct":"88.83"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/general-e2-equivariant-steerable-cnns-1","paper_url":"https://arxiv.org/abs/1911.08251v2","paper_title":"General $E(2)$-Equivariant Steerable CNNs","code":"https://github.com/QUVA-Lab/e2cnn","n_code_links":7,"syntology":null},{"rank_in_archive_order":41,"model":"IIC","metrics":{"Percentage correct":"88.8"},"uses_additional_data":false,"paper_date":"2018-07-17","paper":"/paper/invariant-information-distillation-for","paper_url":"https://arxiv.org/abs/1807.06653v4","paper_title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","code":"https://github.com/xu-ji/IIC","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":16,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"IIC","metrics":{"Percentage correct":"88.80"},"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":43,"model":"SOPCNN","metrics":{"Percentage correct":"88.08"},"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":44,"model":"TS","metrics":{"Percentage correct":"88.03"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/increasing-trustworthiness-of-deep-neural","paper_url":"https://arxiv.org/abs/2007.01472v1","paper_title":"Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":45,"model":"CutOut","metrics":{"Percentage correct":"87.36"},"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":46,"model":"Cutout","metrics":{"Percentage correct":"87.26"},"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":47,"model":"wrn16/8","metrics":{"Percentage correct":"87.26"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/general-e2-equivariant-steerable-cnns-1","paper_url":"https://arxiv.org/abs/1911.08251v2","paper_title":"General $E(2)$-Equivariant Steerable CNNs","code":"https://github.com/QUVA-Lab/e2cnn","n_code_links":7,"syntology":null},{"rank_in_archive_order":48,"model":"Hamiltonian","metrics":{"Percentage correct":"85.5"},"uses_additional_data":false,"paper_date":"2017-09-12","paper":"/paper/reversible-architectures-for-arbitrarily-deep","paper_url":"http://arxiv.org/abs/1709.03698v2","paper_title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","code":"https://github.com/xtractopen/meganet.m","n_code_links":2,"syntology":null},{"rank_in_archive_order":49,"model":"ResNet-18+MM+FRL","metrics":{"Percentage correct":"85.42"},"uses_additional_data":false,"paper_date":"2020-11-22","paper":"/paper/towards-class-specific-unit","paper_url":"https://arxiv.org/abs/2011.10951v2","paper_title":"Learning Class Unique Features in Fine-Grained Visual Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"MidPoint","metrics":{"Percentage correct":"84.6"},"uses_additional_data":false,"paper_date":"2017-09-12","paper":"/paper/reversible-architectures-for-arbitrarily-deep","paper_url":"http://arxiv.org/abs/1709.03698v2","paper_title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","code":"https://github.com/xtractopen/meganet.m","n_code_links":2,"syntology":null},{"rank_in_archive_order":51,"model":"cosine function","metrics":{"Percentage correct":"84.38"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/image-augmentation-for-object-image","paper_url":"https://iopscience.iop.org/article/10.1088/1742-6596/1004/1/012001/pdf","paper_title":"Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":52,"model":"HybridNet","metrics":{"Percentage correct":"84.10"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/hybridnet-classification-and-reconstruction","paper_url":"http://arxiv.org/abs/1807.11407v1","paper_title":"HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"Leapfrog","metrics":{"Percentage correct":"83.7"},"uses_additional_data":false,"paper_date":"2017-09-12","paper":"/paper/reversible-architectures-for-arbitrarily-deep","paper_url":"http://arxiv.org/abs/1709.03698v2","paper_title":"Reversible Architectures for Arbitrarily Deep Residual Neural Networks","code":"https://github.com/xtractopen/meganet.m","n_code_links":2,"syntology":null},{"rank_in_archive_order":54,"model":"skewing","metrics":{"Percentage correct":"83.47"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/image-augmentation-for-object-image","paper_url":"https://iopscience.iop.org/article/10.1088/1742-6596/1004/1/012001/pdf","paper_title":"Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":55,"model":"elastic distortion(2)","metrics":{"Percentage correct":"83.45"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/image-augmentation-for-object-image","paper_url":"https://iopscience.iop.org/article/10.1088/1742-6596/1004/1/012001/pdf","paper_title":"Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":56,"model":"PSLR-knn","metrics":{"Percentage correct":"83.2"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/probabilistic-structural-latent","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Ye_Probabilistic_Structural_Latent_Representation_for_Unsupervised_Embedding_CVPR_2020_paper.html","paper_title":"Probabilistic Structural Latent Representation for Unsupervised Embedding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"elastic distortion(1)","metrics":{"Percentage correct":"83.00"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/image-augmentation-for-object-image","paper_url":"https://iopscience.iop.org/article/10.1088/1742-6596/1004/1/012001/pdf","paper_title":"Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":58,"model":"ResNet baseline","metrics":{"Percentage correct":"82.00"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/hybridnet-classification-and-reconstruction","paper_url":"http://arxiv.org/abs/1807.11407v1","paper_title":"HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":59,"model":"Greedy InfoMax (GIM)","metrics":{"Percentage correct":"81.9"},"uses_additional_data":false,"paper_date":"2019-05-28","paper":"/paper/greedy-infomax-for-biologically-plausible","paper_url":"https://arxiv.org/abs/1905.11786v3","paper_title":"Putting An End to End-to-End: Gradient-Isolated Learning of Representations","code":"https://github.com/loeweX/Greedy_InfoMax","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":60,"model":"rotation","metrics":{"Percentage correct":"81.45"},"uses_additional_data":false,"paper_date":"2018-01-01","paper":"/paper/image-augmentation-for-object-image","paper_url":"https://iopscience.iop.org/article/10.1088/1742-6596/1004/1/012001/pdf","paper_title":"Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"ResNet18(BN, 4)","metrics":{"Percentage correct":"81.04"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":62,"model":"VGG8B + LocalLearning + CO","metrics":{"Percentage correct":"80.75"},"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":63,"model":"ResNet18(GN, 4)","metrics":{"Percentage correct":"79.3"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":64,"model":"PSLR-Linear","metrics":{"Percentage correct":"78.8"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/probabilistic-structural-latent","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Ye_Probabilistic_Structural_Latent_Representation_for_Unsupervised_Embedding_CVPR_2020_paper.html","paper_title":"Probabilistic Structural Latent Representation for Unsupervised Embedding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":65,"model":"ResNet18(BN, 128)","metrics":{"Percentage correct":"78.65"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":66,"model":"Mean Teacher","metrics":{"Percentage correct":"78.57"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":67,"model":"CPC†","metrics":{"Percentage correct":"78.36"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/a-framework-for-contrastive-self-supervised","paper_url":"https://arxiv.org/abs/2009.00104v1","paper_title":"A Framework For Contrastive Self-Supervised Learning And Designing A New Approach","code":"https://github.com/PyTorchLightning/pytorch-lightning","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":68,"model":"Hamiltonian","metrics":{"Percentage correct":"78.3"},"uses_additional_data":false,"paper_date":"2018-04-12","paper":"/paper/deep-neural-networks-motivated-by-partial","paper_url":"http://arxiv.org/abs/1804.04272v2","paper_title":"Deep Neural Networks Motivated by Partial Differential Equations","code":"https://github.com/EmoryMLIP/DynamicBlocks","n_code_links":1,"syntology":null},{"rank_in_archive_order":69,"model":"CC-GAN²","metrics":{"Percentage correct":"77.8"},"uses_additional_data":false,"paper_date":"2016-11-19","paper":"/paper/semi-supervised-learning-with-context","paper_url":"http://arxiv.org/abs/1611.06430v1","paper_title":"Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":70,"model":"CC-GAN","metrics":{"Percentage correct":"77.80"},"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":71,"model":"Parabolic","metrics":{"Percentage correct":"77.0"},"uses_additional_data":false,"paper_date":"2018-04-12","paper":"/paper/deep-neural-networks-motivated-by-partial","paper_url":"http://arxiv.org/abs/1804.04272v2","paper_title":"Deep Neural Networks Motivated by Partial Differential Equations","code":"https://github.com/EmoryMLIP/DynamicBlocks","n_code_links":1,"syntology":null},{"rank_in_archive_order":72,"model":"Scat + WRN 20-8","metrics":{"Percentage correct":"76.6"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":73,"model":"ResNet18(EBN, 4)","metrics":{"Percentage correct":"76.49"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":74,"model":"Exemplar CNN","metrics":{"Percentage correct":"75.7"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":75,"model":"ResNet18(EBN, 128)","metrics":{"Percentage correct":"75.57"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":76,"model":"Stacked what-where AE","metrics":{"Percentage correct":"74.33"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":77,"model":"SWWAE","metrics":{"Percentage correct":"74.33"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/hybridnet-classification-and-reconstruction","paper_url":"http://arxiv.org/abs/1807.11407v1","paper_title":"HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":78,"model":"SWWAE","metrics":{"Percentage correct":"74.30"},"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":79,"model":"SWWAE","metrics":{"Percentage correct":"74.3"},"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":80,"model":"Second-order","metrics":{"Percentage correct":"74.3"},"uses_additional_data":false,"paper_date":"2018-04-12","paper":"/paper/deep-neural-networks-motivated-by-partial","paper_url":"http://arxiv.org/abs/1804.04272v2","paper_title":"Deep Neural Networks Motivated by Partial Differential Equations","code":"https://github.com/EmoryMLIP/DynamicBlocks","n_code_links":1,"syntology":null},{"rank_in_archive_order":81,"model":"Convolutional Clustering","metrics":{"Percentage correct":"74.1"},"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":82,"model":"Π-Model","metrics":{"Percentage correct":"73.77"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":83,"model":"Discriminative Unsupervised Feature Learning with Convolutional Neural Networks","metrics":{"Percentage correct":"72.8"},"uses_additional_data":false,"paper_date":"2014-12-01","paper":"/paper/discriminative-unsupervised-feature-learning-1","paper_url":"http://papers.nips.cc/paper/5548-discriminative-unsupervised-feature-learning-with-convolutional-neural-networks","paper_title":"Discriminative Unsupervised Feature Learning with Convolutional Neural Networks","code":"https://github.com/Octavio-Pappalardo/unsupervised-pretraining-via-self-classification","n_code_links":1,"syntology":null},{"rank_in_archive_order":84,"model":"ResNet18(GN, 128)","metrics":{"Percentage correct":"72.66"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/extended-batch-normalization","paper_url":"https://arxiv.org/abs/2003.05569v1","paper_title":"Extended Batch Normalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":85,"model":"Pseudo-Labeling","metrics":{"Percentage correct":"72.01"},"uses_additional_data":false,"paper_date":"2020-01-21","paper":"/paper/fixmatch-simplifying-semi-supervised-learning-1","paper_url":"https://arxiv.org/pdf/2001.07685.pdf","paper_title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","code":"https://github.com/google-research/fixmatch","n_code_links":1,"syntology":{"n_ran":50,"n_unverified":24,"n_samples":74,"n_pointer_only_licence":14}},{"rank_in_archive_order":86,"model":"Entropy","metrics":{"Percentage correct":"71.65"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/increasing-trustworthiness-of-deep-neural","paper_url":"https://arxiv.org/abs/2007.01472v1","paper_title":"Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":87,"model":"BDW","metrics":{"Percentage correct":"71.12"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/dont-wait-just-weight-improving-unsupervised","paper_url":"https://arxiv.org/pdf/2006.12360.pdf","paper_title":"Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":88,"model":"MP","metrics":{"Percentage correct":"71.05"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/increasing-trustworthiness-of-deep-neural","paper_url":"https://arxiv.org/abs/2007.01472v1","paper_title":"Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":89,"model":"WaveMixLite-256/7","metrics":{"Percentage correct":"70.88"},"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":90,"model":"CNN","metrics":{"Percentage correct":"70.7"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":91,"model":"An Analysis of Unsupervised Pre-training in Light of Recent Advances","metrics":{"Percentage correct":"70.2"},"uses_additional_data":false,"paper_date":"2014-12-20","paper":"/paper/an-analysis-of-unsupervised-pre-training-in","paper_url":"http://arxiv.org/abs/1412.6597v4","paper_title":"An Analysis of Unsupervised Pre-training in Light of Recent Advances","code":"https://github.com/ifp-uiuc/anna","n_code_links":2,"syntology":null},{"rank_in_archive_order":92,"model":"Multi-Task Bayesian Optimization","metrics":{"Percentage correct":"70.1"},"uses_additional_data":false,"paper_date":"2013-12-01","paper":"/paper/multi-task-bayesian-optimization","paper_url":"http://papers.nips.cc/paper/5086-multi-task-bayesian-optimization","paper_title":"Multi-Task Bayesian Optimization","code":"https://github.com/HIPS/Spearmint","n_code_links":1,"syntology":null},{"rank_in_archive_order":93,"model":"NN-Weighter","metrics":{"Percentage correct":"69.15"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/dont-wait-just-weight-improving-unsupervised","paper_url":"https://arxiv.org/pdf/2006.12360.pdf","paper_title":"Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":94,"model":"Accuracy Monitoring","metrics":{"Percentage correct":"68.62"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/increasing-trustworthiness-of-deep-neural","paper_url":"https://arxiv.org/abs/2007.01472v1","paper_title":"Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":95,"model":"C-SVDDNet","metrics":{"Percentage correct":"68.2"},"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":96,"model":"RotNet","metrics":{"Percentage correct":"68.19"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/dont-wait-just-weight-improving-unsupervised","paper_url":"https://arxiv.org/pdf/2006.12360.pdf","paper_title":"Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":97,"model":"DFF Committees","metrics":{"Percentage correct":"68"},"uses_additional_data":false,"paper_date":"2014-06-23","paper":"/paper/committees-of-deep-feedforward-networks","paper_url":"http://arxiv.org/abs/1406.5947v1","paper_title":"Committees of deep feedforward networks trained with few data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":98,"model":"Hierarchical Matching Pursuit (HMP)","metrics":{"Percentage correct":"64.6"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":99,"model":"L2RW","metrics":{"Percentage correct":"63.13"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/dont-wait-just-weight-improving-unsupervised","paper_url":"https://arxiv.org/pdf/2006.12360.pdf","paper_title":"Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":100,"model":"Discriminative Learning of Sum-Product Networks","metrics":{"Percentage correct":"62.3"},"uses_additional_data":false,"paper_date":"2011-01-01","paper":"/paper/discriminative-learning-of-sum-product","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0893608019303946","paper_title":"Discriminative Learning of Sum-Product Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":101,"model":"CKN","metrics":{"Percentage correct":"62.3"},"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":102,"model":"S-CNN","metrics":{"Percentage correct":"61.94"},"uses_additional_data":false,"paper_date":"2016-06-07","paper":"/paper/selective-unsupervised-feature-learning-with","paper_url":"http://arxiv.org/abs/1606.02210v1","paper_title":"Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":103,"model":"Simulated Fixations","metrics":{"Percentage correct":"61"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/a-framework-for-contrastive-self-supervised","paper_url":"https://arxiv.org/abs/2009.00104v1","paper_title":"A Framework For Contrastive Self-Supervised Learning And Designing A New Approach","code":"https://github.com/PyTorchLightning/pytorch-lightning","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":104,"model":"No more meta-parameter tuning in unsupervised sparse feature learning","metrics":{"Percentage correct":"61"},"uses_additional_data":false,"paper_date":"2014-02-24","paper":"/paper/no-more-meta-parameter-tuning-in-unsupervised","paper_url":"http://arxiv.org/abs/1402.5766v1","paper_title":"No more meta-parameter tuning in unsupervised sparse feature learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":105,"model":"Convolutional K-means Network","metrics":{"Percentage correct":"60.2"},"uses_additional_data":false,"paper_date":"2017-03-27","paper":"/paper/scaling-the-scattering-transform-deep-hybrid","paper_url":"http://arxiv.org/abs/1703.08961v2","paper_title":"Scaling the Scattering Transform: Deep Hybrid Networks","code":"https://github.com/edouardoyallon/pyscatwave","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":106,"model":"Receptive Fields","metrics":{"Percentage correct":"60.1"},"uses_additional_data":false,"paper_date":"2007-12-01","paper":"/paper/receptive-fields-without-spike-triggering","paper_url":"http://papers.nips.cc/paper/3220-receptive-fields-without-spike-triggering","paper_title":"Receptive Fields without Spike-Triggering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":107,"model":"PWD","metrics":{"Percentage correct":"59.45"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":108,"model":"GVD","metrics":{"Percentage correct":"59.33"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":109,"model":"VR","metrics":{"Percentage correct":"59.13"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":110,"model":"Core SET","metrics":{"Percentage correct":"58.93"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":111,"model":"GE","metrics":{"Percentage correct":"58.84"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":112,"model":"DFAL","metrics":{"Percentage correct":"58.81"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":113,"model":"Random","metrics":{"Percentage correct":"58.15"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":114,"model":"BALD-MCD","metrics":{"Percentage correct":"57.35"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":115,"model":"Sign-symmetry","metrics":{"Percentage correct":"57.32"},"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":116,"model":"M2-PWD","metrics":{"Percentage correct":"57.31"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/effective-version-space-reduction-for","paper_url":"https://arxiv.org/abs/2006.12456v1","paper_title":"Effective Version Space Reduction for Convolutional Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":117,"model":"soft ica","metrics":{"Percentage correct":"52.9"},"uses_additional_data":false,"paper_date":"2011-12-01","paper":"/paper/ica-with-reconstruction-cost-for-efficient","paper_url":"http://papers.nips.cc/paper/4467-ica-with-reconstruction-cost-for-efficient-overcomplete-feature-learning","paper_title":"ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning","code":null,"n_code_links":0,"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":39,"rows_with_any_sample_ran":29,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":129,"n_unverified":94,"n_samples":223,"n_pointer_only_licence":60,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":571,"n_unverified":331,"n_samples":902,"n_pointer_only_licence":239,"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"}}}