{"url":"/sota/image-classification-on-mini-webvision-1-0","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"mini WebVision 1.0","url":"/dataset/webvision-database"},"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":["Top-1 Accuracy","Top-5 Accuracy","ImageNet Top-1 Accuracy","ImageNet Top-5 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top-1 Accuracy":"higher","Top-5 Accuracy":"higher","ImageNet Top-1 Accuracy":"higher","ImageNet Top-5 Accuracy":"higher"}},"counts":{"rows":47,"rows_with_code":36,"rows_with_paper_page":47,"rows_dated":47,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LRA-diffusion (CLIP ViT)","metrics":{"ImageNet Top-1 Accuracy":"82.56","Top-1 Accuracy":"84.16"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/label-retrieval-augmented-diffusion-models-1","paper_url":"https://arxiv.org/abs/2305.19518v2","paper_title":"Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels","code":"https://github.com/puar-playground/lra-diffusion","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Robust LR","metrics":{"ImageNet Top-1 Accuracy":"75.48","ImageNet Top-5 Accuracy":"93.76","Top-1 Accuracy":"81.84","Top-5 Accuracy":"94.12"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/two-wrongs-don-t-make-a-right-combating","paper_url":"https://arxiv.org/abs/2112.02960v3","paper_title":"Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"PGDF (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"75.45","ImageNet Top-5 Accuracy":"93.11","Top-1 Accuracy":"81.47","Top-5 Accuracy":"94.03"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/sample-prior-guided-robust-model-learning-to","paper_url":"https://arxiv.org/abs/2112.01197v3","paper_title":"Sample Prior Guided Robust Model Learning to Suppress Noisy Labels","code":"https://github.com/bupt-ai-cz/PGDF","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SSR","metrics":{"ImageNet Top-1 Accuracy":"75.76","ImageNet Top-5 Accuracy":"91.76","Top-1 Accuracy":"80.92","Top-5 Accuracy":"92.80"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/s3-supervised-self-supervised-learning-under-1","paper_url":"https://arxiv.org/abs/2111.11288v2","paper_title":"SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise","code":"https://github.com/MrChenFeng/SSR_BMVC2022","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"BtR","metrics":{"ImageNet Top-1 Accuracy":"75.96","ImageNet Top-5 Accuracy":"92.20","Top-1 Accuracy":"80.88","Top-5 Accuracy":"92.76"},"uses_additional_data":false,"paper_date":"2022-10-17","paper":"/paper/bootstrapping-the-relationship-between-images","paper_url":"https://arxiv.org/abs/2210.08826v1","paper_title":"Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels","code":"https://github.com/btsmart/bootstrapping-label-noise","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CoDiM-Sup (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"76.52","ImageNet Top-5 Accuracy":"91.96","Top-1 Accuracy":"80.88","Top-5 Accuracy":"92.48"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/codim-learning-with-noisy-labels-via","paper_url":"https://arxiv.org/abs/2111.11652v1","paper_title":"CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"NCR+Mixup+DA (ResNet-50)","metrics":{"Top-1 Accuracy":"80.5"},"uses_additional_data":false,"paper_date":"2022-02-04","paper":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_url":"https://arxiv.org/abs/2202.02200v2","paper_title":"Learning with Neighbor Consistency for Noisy Labels","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"CMW-Net-SL+C2D","metrics":{"ImageNet Top-1 Accuracy":"77.36","ImageNet Top-5 Accuracy":"93.48","Top-1 Accuracy":"80.44","Top-5 Accuracy":"93.36"},"uses_additional_data":false,"paper_date":"2022-02-11","paper":"/paper/cmw-net-learning-a-class-aware-sample","paper_url":"https://arxiv.org/abs/2202.05613v3","paper_title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","code":"https://github.com/xjtushujun/cmw-net","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":9,"model":"Dynamic Loss  (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"74.76","ImageNet Top-5 Accuracy":"93.08","Top-1 Accuracy":"80.12","Top-5 Accuracy":"93.64"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/dynamic-loss-for-robust-learning","paper_url":"https://arxiv.org/abs/2211.12506v2","paper_title":"Dynamic Loss For Robust Learning","code":"https://github.com/jiangwenj02/dynamic_loss","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CoDiM-Self  (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"77.24","ImageNet Top-5 Accuracy":"92.48","Top-1 Accuracy":"80.12","Top-5 Accuracy":"93.52"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/codim-learning-with-noisy-labels-via","paper_url":"https://arxiv.org/abs/2111.11652v1","paper_title":"CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Sel-CL+ (ResNet-18)","metrics":{"ImageNet Top-1 Accuracy":"76.84","ImageNet Top-5 Accuracy":"93.04","Top-1 Accuracy":"79.96","Top-5 Accuracy":"92.64"},"uses_additional_data":false,"paper_date":"2022-03-08","paper":"/paper/selective-supervised-contrastive-learning","paper_url":"https://arxiv.org/abs/2203.04181v1","paper_title":"Selective-Supervised Contrastive Learning with Noisy Labels","code":"https://github.com/shikunli/sel-cl","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":"CPC","metrics":{"ImageNet Top-1 Accuracy":"75.75±0.14","ImageNet Top-5 Accuracy":"93.49±0.25","Top-1 Accuracy":"79.63±0.08","Top-5 Accuracy":"93.46±0.10"},"uses_additional_data":false,"paper_date":"2022-12-21","paper":"/paper/class-prototype-based-cleaner-for-label-noise","paper_url":"https://arxiv.org/abs/2212.10766v1","paper_title":"Class Prototype-based Cleaner for Label Noise Learning","code":"https://github.com/hjjpku/cpc","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PSSCL (130 epochs)","metrics":{"ImageNet Top-1 Accuracy":"79.68","ImageNet Top-5 Accuracy":"95.16","Top-1 Accuracy":"79.56","Top-5 Accuracy":"94.84"},"uses_additional_data":false,"paper_date":"2024-12-18","paper":"/paper/psscl-a-progressive-sample-selection","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0031320324010355","paper_title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","code":"https://github.com/LanXiaoPang613/PSSCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"DivideMix with C2D (ResNet-50)","metrics":{"ImageNet Top-1 Accuracy":"78.57 ± 0.37","ImageNet Top-5 Accuracy":"93.04 ± 0.10","Top-1 Accuracy":"79.42 ± 0.34","Top-5 Accuracy":"92.32 ± 0.33"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/contrast-to-divide-self-supervised-pre-1","paper_url":"https://arxiv.org/abs/2103.13646v2","paper_title":"Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels","code":"https://github.com/ContrastToDivide/C2D","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"FaMUS","metrics":{"ImageNet Top-1 Accuracy":"77","ImageNet Top-5 Accuracy":"92.76","Top-1 Accuracy":"79.4","Top-5 Accuracy":"92.80"},"uses_additional_data":false,"paper_date":"2021-04-30","paper":"/paper/faster-meta-update-strategy-for-noise-robust","paper_url":"https://arxiv.org/abs/2104.15092v1","paper_title":"Faster Meta Update Strategy for Noise-Robust Deep Learning","code":"https://github.com/youjiangxu/FaMUS","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":16,"model":"NCR+Mixup (ResNet-50)","metrics":{"Top-1 Accuracy":"79.4"},"uses_additional_data":false,"paper_date":"2022-02-04","paper":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_url":"https://arxiv.org/abs/2202.02200v2","paper_title":"Learning with Neighbor Consistency for Noisy Labels","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CC","metrics":{"ImageNet Top-1 Accuracy":"76.08","ImageNet Top-5 Accuracy":"93.86","Top-1 Accuracy":"79.36","Top-5 Accuracy":"93.64"},"uses_additional_data":false,"paper_date":"2022-07-29","paper":"/paper/centrality-and-consistency-two-stage-clean","paper_url":"https://arxiv.org/abs/2207.14476v1","paper_title":"Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels","code":"https://github.com/uitrbn/tscsi_idn","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"GJS (ResNet-50)","metrics":{"ImageNet Top-1 Accuracy":"75.50","ImageNet Top-5 Accuracy":"91.27","Top-1 Accuracy":"79.28","Top-5 Accuracy":"91.22"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/generalized-jensen-shannon-divergence-loss","paper_url":"https://arxiv.org/abs/2105.04522v4","paper_title":"Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels","code":"https://github.com/erikenglesson/gjs","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":19,"model":"NGC (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"74.44 ","ImageNet Top-5 Accuracy":"91.04","Top-1 Accuracy":"79.16","Top-5 Accuracy":"91.84 "},"uses_additional_data":false,"paper_date":"2021-08-25","paper":"/paper/ngc-a-unified-framework-for-learning-with","paper_url":"https://arxiv.org/abs/2108.11035v1","paper_title":"NGC: A Unified Framework for Learning with Open-World Noisy Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"TCL","metrics":{"ImageNet Top-1 Accuracy":"75.4","ImageNet Top-5 Accuracy":"92.4","Top-1 Accuracy":"79.1","Top-5 Accuracy":"92.3"},"uses_additional_data":false,"paper_date":"2023-03-13","paper":"/paper/twin-contrastive-learning-with-noisy-labels","paper_url":"https://arxiv.org/abs/2303.06930v1","paper_title":"Twin Contrastive Learning with Noisy Labels","code":"https://github.com/hzzone/tcl","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"LongReMix (Inception-ResNet-v2)","metrics":{"Top-1 Accuracy":"78.92","Top-5 Accuracy":"92.32"},"uses_additional_data":false,"paper_date":"2021-03-06","paper":"/paper/longremix-robust-learning-with-high","paper_url":"https://arxiv.org/abs/2103.04173v2","paper_title":"LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment","code":"https://github.com/filipe-research/LongReMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"MOIT+ (ResNet-18)","metrics":{"Top-1 Accuracy":"78.76"},"uses_additional_data":false,"paper_date":"2020-12-08","paper":"/paper/multi-objective-interpolation-training-for","paper_url":"https://arxiv.org/abs/2012.04462v2","paper_title":"Multi-Objective Interpolation Training for Robustness to Label Noise","code":"https://github.com/DiegoOrtego/LabelNoiseMOIT","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"PSSCL (120 epochs)","metrics":{"ImageNet Top-1 Accuracy":"79.40","ImageNet Top-5 Accuracy":"94.84","Top-1 Accuracy":"78.52","Top-5 Accuracy":"93.80"},"uses_additional_data":false,"paper_date":"2024-12-18","paper":"/paper/psscl-a-progressive-sample-selection","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0031320324010355","paper_title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","code":"https://github.com/LanXiaoPang613/PSSCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"CMW-Net-SL","metrics":{"ImageNet Top-1 Accuracy":"75.72","ImageNet Top-5 Accuracy":"92.52","Top-1 Accuracy":"78.08","Top-5 Accuracy":"92.96"},"uses_additional_data":false,"paper_date":"2022-02-11","paper":"/paper/cmw-net-learning-a-class-aware-sample","paper_url":"https://arxiv.org/abs/2202.05613v3","paper_title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","code":"https://github.com/xjtushujun/cmw-net","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":25,"model":"ELR+ (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"70.29","ImageNet Top-5 Accuracy":"89.76","Top-1 Accuracy":"77.78","Top-5 Accuracy":"91.68"},"uses_additional_data":false,"paper_date":"2020-06-30","paper":"/paper/early-learning-regularization-prevents","paper_url":"https://arxiv.org/abs/2007.00151v2","paper_title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","code":"https://github.com/shengliu66/ELR","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"ScanMix (Inception-ResNet-v2)","metrics":{"Top-1 Accuracy":"77.72"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/scanmix-learning-from-severe-label-noise-via","paper_url":"https://arxiv.org/abs/2103.11395v3","paper_title":"ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning","code":"https://github.com/ragavsachdeva/ScanMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"ROLT+ (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"74.64","ImageNet Top-5 Accuracy":"92.48","Top-1 Accuracy":"77.64","Top-5 Accuracy":"92.44"},"uses_additional_data":false,"paper_date":"2021-08-26","paper":"/paper/robust-long-tailed-learning-under-label-noise","paper_url":"https://arxiv.org/abs/2108.11569v1","paper_title":"Robust Long-Tailed Learning under Label Noise","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"CNLCU-S + DivideMix (Inception-ResNet-v2)","metrics":{"Top-1 Accuracy":"77.53"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/sample-selection-with-uncertainty-of-losses","paper_url":"https://arxiv.org/abs/2106.00445v1","paper_title":"Sample Selection with Uncertainty of Losses for Learning with Noisy Labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"HSA-NRL(Inception-ResNet-v2)","metrics":{"Top-1 Accuracy":"77.52"},"uses_additional_data":false,"paper_date":"2021-12-05","paper":"/paper/hard-sample-aware-noise-robust-learning-for","paper_url":"https://arxiv.org/abs/2112.03694v1","paper_title":"Hard Sample Aware Noise Robust Learning for Histopathology Image Classification","code":"https://github.com/bupt-ai-cz/HSA-NRL","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"CAR","metrics":{"ImageNet Top-1 Accuracy":"74.09","ImageNet Top-5 Accuracy":"92.09","Top-1 Accuracy":"77.41","Top-5 Accuracy":"92.25"},"uses_additional_data":false,"paper_date":"2021-08-18","paper":"/paper/confidence-adaptive-regularization-for-deep","paper_url":"https://arxiv.org/abs/2108.08212v2","paper_title":"Confidence Adaptive Regularization for Deep Learning with Noisy Labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"DivideMix (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"75.20","ImageNet Top-5 Accuracy":"91.64","Top-1 Accuracy":"77.32","Top-5 Accuracy":"91.64"},"uses_additional_data":false,"paper_date":"2020-02-18","paper":"/paper/dividemix-learning-with-noisy-labels-as-semi-1","paper_url":"https://arxiv.org/abs/2002.07394v1","paper_title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","code":"https://github.com/LiJunnan1992/DivideMix","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":32,"model":"NCR (ResNet-50)","metrics":{"Top-1 Accuracy":"77.1"},"uses_additional_data":false,"paper_date":"2022-02-04","paper":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_url":"https://arxiv.org/abs/2202.02200v2","paper_title":"Learning with Neighbor Consistency for Noisy Labels","code":"https://github.com/google-research/scenic","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"DivideMix (ResNet-50)","metrics":{"ImageNet Top-1 Accuracy":"74.42 ±0.29","ImageNet Top-5 Accuracy":"91.21 ±0.12","Top-1 Accuracy":"76.32 ±0.36","Top-5 Accuracy":"90.65 ±0.16"},"uses_additional_data":false,"paper_date":"2020-02-18","paper":"/paper/dividemix-learning-with-noisy-labels-as-semi-1","paper_url":"https://arxiv.org/abs/2002.07394v1","paper_title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","code":"https://github.com/LiJunnan1992/DivideMix","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":34,"model":"DivideMix (ResNet-18)","metrics":{"Top-1 Accuracy":"76.08"},"uses_additional_data":false,"paper_date":"2020-02-18","paper":"/paper/dividemix-learning-with-noisy-labels-as-semi-1","paper_url":"https://arxiv.org/abs/2002.07394v1","paper_title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","code":"https://github.com/LiJunnan1992/DivideMix","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":35,"model":"MentorMix (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"72.9","ImageNet Top-5 Accuracy":"91.1","Top-1 Accuracy":"76.0","Top-5 Accuracy":"90.2"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/synthetic-vs-real-deep-learning-on-controlled-1","paper_url":"https://arxiv.org/abs/1911.09781v3","paper_title":"Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels","code":"https://github.com/google-research/google-research/tree/master/mentormix","n_code_links":3,"syntology":null},{"rank_in_archive_order":36,"model":"NCT (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"71.73","ImageNet Top-5 Accuracy":"91.61","Top-1 Accuracy":"75.16","Top-5 Accuracy":"90.77"},"uses_additional_data":false,"paper_date":"2020-09-17","paper":"/paper/noisy-concurrent-training-for-efficient","paper_url":"https://arxiv.org/abs/2009.08325v1","paper_title":"Noisy Concurrent Training for Efficient Learning under Label Noise","code":"https://github.com/NeurAI-Lab/UniNet","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"ODD (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"66.7","ImageNet Top-5 Accuracy":"86.3","Top-1 Accuracy":"74.6","Top-5 Accuracy":"90.6"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/robust-and-on-the-fly-dataset-denoising-for","paper_url":"https://arxiv.org/abs/2003.10647v2","paper_title":"Robust and On-the-fly Dataset Denoising for Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"Crust (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"67.36","ImageNet Top-5 Accuracy":"87.84","Top-1 Accuracy":"72.40","Top-5 Accuracy":"89.56"},"uses_additional_data":false,"paper_date":"2020-11-15","paper":"/paper/coresets-for-robust-training-of-neural","paper_url":"https://arxiv.org/abs/2011.07451v1","paper_title":"Coresets for Robust Training of Neural Networks against Noisy Labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"Iterative-CV (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"61.6","ImageNet Top-5 Accuracy":"85.0","Top-1 Accuracy":"65.2","Top-5 Accuracy":"85.3"},"uses_additional_data":false,"paper_date":"2019-05-13","paper":"/paper/understanding-and-utilizing-deep-neural","paper_url":"https://arxiv.org/abs/1905.05040v1","paper_title":"Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels","code":"https://github.com/chenpf1025/noisy_label_understanding_utilizing","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":40,"model":"Co-teaching (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"61.48","ImageNet Top-5 Accuracy":"84.70","Top-1 Accuracy":"63.58","Top-5 Accuracy":"85.20"},"uses_additional_data":false,"paper_date":"2018-04-18","paper":"/paper/co-teaching-robust-training-of-deep-neural","paper_url":"http://arxiv.org/abs/1804.06872v3","paper_title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","code":"https://github.com/bhanML/Co-teaching","n_code_links":5,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":41,"model":"D2L (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"57.80","ImageNet Top-5 Accuracy":"81.36","Top-1 Accuracy":"62.68","Top-5 Accuracy":"84.00"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/dimensionality-driven-learning-with-noisy","paper_url":"http://arxiv.org/abs/1806.02612v2","paper_title":"Dimensionality-Driven Learning with Noisy Labels","code":"https://github.com/ansuini/IntrinsicDimDeep","n_code_links":3,"syntology":null},{"rank_in_archive_order":42,"model":"F-Correction (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"57.36","ImageNet Top-5 Accuracy":"82.36","Top-1 Accuracy":"61.12","Top-5 Accuracy":"82.68"},"uses_additional_data":false,"paper_date":"2016-09-13","paper":"/paper/making-deep-neural-networks-robust-to-label","paper_url":"http://arxiv.org/abs/1609.03683v2","paper_title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","code":"https://github.com/yikun2019/PENCIL","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":43,"model":"RTE (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"80.84","ImageNet Top-5 Accuracy":"97.24"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/robust-temporal-ensembling-for-learning-with","paper_url":"https://arxiv.org/abs/2109.14563v1","paper_title":"Robust Temporal Ensembling for Learning with Noisy Labels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"MentorNet (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"63.8","ImageNet Top-5 Accuracy":"85.8"},"uses_additional_data":false,"paper_date":"2017-12-14","paper":"/paper/mentornet-learning-data-driven-curriculum-for","paper_url":"http://arxiv.org/abs/1712.05055v2","paper_title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","code":"https://github.com/google/mentornet","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"NCE+RCE (ResNet-50)","metrics":{"ImageNet Top-1 Accuracy":"62.64"},"uses_additional_data":false,"paper_date":"2020-06-24","paper":"/paper/normalized-loss-functions-for-deep-learning","paper_url":"https://arxiv.org/abs/2006.13554v1","paper_title":"Normalized Loss Functions for Deep Learning with Noisy Labels","code":"https://github.com/HanxunH/Active-Passive-Losses","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"NCE+MAE (ResNet-50)","metrics":{"ImageNet Top-1 Accuracy":"62.36"},"uses_additional_data":false,"paper_date":"2020-06-24","paper":"/paper/normalized-loss-functions-for-deep-learning","paper_url":"https://arxiv.org/abs/2006.13554v1","paper_title":"Normalized Loss Functions for Deep Learning with Noisy Labels","code":"https://github.com/HanxunH/Active-Passive-Losses","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"CDR (Inception-ResNet-v2)","metrics":{"ImageNet Top-1 Accuracy":"61.85"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/robust-early-learning-hindering-the","paper_url":"https://openreview.net/forum?id=Eql5b1_hTE4","paper_title":"Robust early-learning: Hindering the memorization of noisy labels","code":null,"n_code_links":0,"syntology":null}],"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":21,"rows_with_any_sample_ran":18,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":49,"n_unverified":29,"n_samples":78,"n_pointer_only_licence":30,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":60,"n_unverified":45,"n_samples":105,"n_pointer_only_licence":37,"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"}}}