{"url":"/task/learning-with-noisy-labels","name":"Learning with noisy labels","slug":"learning-with-noisy-labels","description_markdown":"Learning with noisy labels means When we say \"noisy labels,\" we mean that an adversary has intentionally messed up the labels, which would have come from a \"clean\" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":249,"papers_with_code":143,"benchmarks":20,"benchmark_tables_in_archive":20,"benchmark_tables_shown":20,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n","slug":"learning-with-noisy-labels-on-cifar-10n","dataset":"CIFAR-10N-Aggregate","dataset_url":"/dataset/cifar-10n","rows_in_archive":26,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"ProMix","paper_title":"ProMix: Combating Label Noise via Maximizing Clean Sample Utility","paper_url":"/paper/promix-combating-label-noise-via-maximizing","paper_date":"2022-07-21","arxiv_id":"2207.10276","code_links":[{"title":"justherozen/promix","url":"https://github.com/justherozen/promix"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-worst","slug":"learning-with-noisy-labels-on-cifar-10n-worst","dataset":"CIFAR-10N-Worst","dataset_url":"/dataset/cifar-10n","rows_in_archive":25,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"ProMix","paper_title":"ProMix: Combating Label Noise via Maximizing Clean Sample Utility","paper_url":"/paper/promix-combating-label-noise-via-maximizing","paper_date":"2022-07-21","arxiv_id":"2207.10276","code_links":[{"title":"justherozen/promix","url":"https://github.com/justherozen/promix"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100n","slug":"learning-with-noisy-labels-on-cifar-100n","dataset":"CIFAR-100N","dataset_url":"/dataset/cifar-100n","rows_in_archive":24,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"PGDF","paper_title":"Sample Prior Guided Robust Model Learning to Suppress Noisy Labels","paper_url":"/paper/sample-prior-guided-robust-model-learning-to","paper_date":"2021-12-02","arxiv_id":"2112.01197","code_links":[{"title":"bupt-ai-cz/PGDF","url":"https://github.com/bupt-ai-cz/PGDF"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-1","slug":"learning-with-noisy-labels-on-cifar-10n-1","dataset":"CIFAR-10N-Random1","dataset_url":"/dataset/cifar-10n","rows_in_archive":24,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"ProMix","paper_title":"ProMix: Combating Label Noise via Maximizing Clean Sample Utility","paper_url":"/paper/promix-combating-label-noise-via-maximizing","paper_date":"2022-07-21","arxiv_id":"2207.10276","code_links":[{"title":"justherozen/promix","url":"https://github.com/justherozen/promix"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-2","slug":"learning-with-noisy-labels-on-cifar-10n-2","dataset":"CIFAR-10N-Random2","dataset_url":"/dataset/cifar-10n","rows_in_archive":23,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"PSSCL","paper_title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","paper_url":"/paper/psscl-a-progressive-sample-selection","paper_date":"2024-12-18","arxiv_id":null,"code_links":[{"title":"LanXiaoPang613/PSSCL","url":"https://github.com/LanXiaoPang613/PSSCL"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-3","slug":"learning-with-noisy-labels-on-cifar-10n-3","dataset":"CIFAR-10N-Random3","dataset_url":"/dataset/cifar-10n","rows_in_archive":23,"metrics":["Accuracy (mean)"],"first_row_in_archive_order":{"model":"PSSCL","paper_title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","paper_url":"/paper/psscl-a-progressive-sample-selection","paper_date":"2024-12-18","arxiv_id":null,"code_links":[{"title":"LanXiaoPang613/PSSCL","url":"https://github.com/LanXiaoPang613/PSSCL"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","slug":"learning-with-noisy-labels-on-animal","dataset":"ANIMAL","dataset_url":"/dataset/animal","rows_in_archive":19,"metrics":["Accuracy","Network","ImageNet Pretrained"],"first_row_in_archive_order":{"model":"Jigsaw-ViT","paper_title":"Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer","paper_url":"/paper/jigsaw-vit-learning-jigsaw-puzzles-in-vision","paper_date":"2022-07-25","arxiv_id":"2207.11971","code_links":[{"title":"yingyichen-cyy/JigsawViT","url":"https://github.com/yingyichen-cyy/JigsawViT"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-clothing1m","slug":"learning-with-noisy-labels-on-clothing1m","dataset":"Clothing1M","dataset_url":"/dataset/clothing1m","rows_in_archive":5,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"Knockoffs-SPR","paper_title":"Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels","paper_url":"/paper/knockoffs-spr-clean-sample-selection-in","paper_date":"2023-01-02","arxiv_id":"2301.00545","code_links":[{"title":"yikai-wang/knockoffs-spr","url":"https://github.com/yikai-wang/knockoffs-spr"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-red","slug":"learning-with-noisy-labels-on-red","dataset":"Red MiniImageNet 20% label noise","dataset_url":"/dataset/red-miniimagenet-20-label-noise","rows_in_archive":4,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"NCR (ResNet-18)","paper_title":"Learning with Neighbor Consistency for Noisy Labels","paper_url":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_date":"2022-02-04","arxiv_id":"2202.02200","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-1","slug":"learning-with-noisy-labels-on-red-1","dataset":"Red MiniImageNet 40% label noise","dataset_url":"/dataset/red-miniimagenet-40-label-noise","rows_in_archive":4,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"NCR (ResNet-18)","paper_title":"Learning with Neighbor Consistency for Noisy Labels","paper_url":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_date":"2022-02-04","arxiv_id":"2202.02200","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-3","slug":"learning-with-noisy-labels-on-red-3","dataset":"Red MiniImageNet 80% label noise","dataset_url":"/dataset/red-miniimagenet-80-label-noise","rows_in_archive":4,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"NCR (ResNet-18)","paper_title":"Learning with Neighbor Consistency for Noisy Labels","paper_url":"/paper/learning-with-neighbor-consistency-for-noisy-1","paper_date":"2022-02-04","arxiv_id":"2202.02200","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-food-101","slug":"learning-with-noisy-labels-on-food-101","dataset":"Food-101","dataset_url":"/dataset/food-101","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LongReMix","paper_title":"LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment","paper_url":"/paper/longremix-robust-learning-with-high","paper_date":"2021-03-06","arxiv_id":"2103.04173","code_links":[{"title":"filipe-research/LongReMix","url":"https://github.com/filipe-research/LongReMix"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-2","slug":"learning-with-noisy-labels-on-red-2","dataset":"Red MiniImageNet 60% label noise","dataset_url":null,"rows_in_archive":3,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"InstanceGM-SS","paper_title":"Instance-Dependent Noisy Label Learning via Graphical Modelling","paper_url":"/paper/instance-dependent-noisy-label-learning-via","paper_date":"2022-09-02","arxiv_id":"2209.00906","code_links":[{"title":"arpit2412/InstanceGM","url":"https://github.com/arpit2412/InstanceGM"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-chaoyang","slug":"learning-with-noisy-labels-on-chaoyang","dataset":"Chaoyang","dataset_url":"/dataset/chaoyang","rows_in_archive":1,"metrics":["ACCURACY"],"first_row_in_archive_order":{"model":"HSANR","paper_title":"Hard Sample Aware Noise Robust Learning for Histopathology Image Classification","paper_url":"/paper/hard-sample-aware-noise-robust-learning-for","paper_date":"2021-12-05","arxiv_id":"2112.03694","code_links":[{"title":"bupt-ai-cz/HSA-NRL","url":"https://github.com/bupt-ai-cz/HSA-NRL"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10","slug":"learning-with-noisy-labels-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"InstanceGM","paper_title":"Instance-Dependent Noisy Label Learning via Graphical Modelling","paper_url":"/paper/instance-dependent-noisy-label-learning-via","paper_date":"2022-09-02","arxiv_id":"2209.00906","code_links":[{"title":"arpit2412/InstanceGM","url":"https://github.com/arpit2412/InstanceGM"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100","slug":"learning-with-noisy-labels-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":1,"metrics":["Test Accuracy"],"first_row_in_archive_order":{"model":"InstanceGM","paper_title":"Instance-Dependent Noisy Label Learning via Graphical Modelling","paper_url":"/paper/instance-dependent-noisy-label-learning-via","paper_date":"2022-09-02","arxiv_id":"2209.00906","code_links":[{"title":"arpit2412/InstanceGM","url":"https://github.com/arpit2412/InstanceGM"}],"syntology":null}},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-4","slug":"learning-with-noisy-labels-on-cifar-10n-4","dataset":"CIFAR-10N","dataset_url":"/dataset/cifar-10n","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ProMix","paper_title":"ProMix: Combating Label Noise via Maximizing Clean Sample Utility","paper_url":"/paper/promix-combating-label-noise-via-maximizing","paper_date":"2022-07-21","arxiv_id":"2207.10276","code_links":[{"title":"justherozen/promix","url":"https://github.com/justherozen/promix"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-clothing1m-2","slug":"learning-with-noisy-labels-on-clothing1m-2","dataset":"Clothing1M (using clean data)","dataset_url":"/dataset/clothing1m","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"ResNet50","paper_title":"UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning","paper_url":"/paper/unicon-combating-label-noise-through-uniform","paper_date":"2022-03-28","arxiv_id":"2203.14542","code_links":[{"title":"nazmul-karim170/unicon-noisy-label","url":"https://github.com/nazmul-karim170/unicon-noisy-label"}],"syntology":{"n":15,"n_ran":7,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-coco-wan","slug":"learning-with-noisy-labels-on-coco-wan","dataset":"COCO-WAN","dataset_url":"/dataset/coco-wan-medium-noise","rows_in_archive":1,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"Mask R-CNN (ResNet-50-FPN)","paper_title":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters","paper_url":"/paper/benchmarking-label-noise-in-instance","paper_date":"2024-06-16","arxiv_id":"2406.10891","code_links":[{"title":"eden500/Noisy-Labels-Instance-Segmentation","url":"https://github.com/eden500/Noisy-Labels-Instance-Segmentation"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-noisy-labels-on-mini-webvision","slug":"learning-with-noisy-labels-on-mini-webvision","dataset":"mini WebVision 1.0","dataset_url":"/dataset/webvision-database","rows_in_archive":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"ILL","paper_title":"Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations","paper_url":"/paper/imprecise-label-learning-a-unified-framework","paper_date":"2023-05-22","arxiv_id":"2305.12715","code_links":[{"title":"hhhhhhao/general-framework-weak-supervision","url":"https://github.com/hhhhhhao/general-framework-weak-supervision"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/clothing1m","name":"Clothing1M","full_name":"","num_papers_in_archive":288},{"url":"/dataset/webvision-database","name":"WebVision","full_name":"","num_papers_in_archive":179},{"url":"/dataset/cifar-10n","name":"CIFAR-10N","full_name":"Real-World Human Annotations","num_papers_in_archive":97},{"url":"/dataset/cifar-100n","name":"CIFAR-100N","full_name":"Real-World Human Annotations","num_papers_in_archive":66},{"url":"/dataset/chaoyang","name":"Chaoyang","full_name":"","num_papers_in_archive":19},{"url":"/dataset/animal","name":"ANIMAL","full_name":"ANIMAL-10N","num_papers_in_archive":15},{"url":"/dataset/galaxy-zoo-decals","name":"Galaxy Zoo DECaLS","full_name":"","num_papers_in_archive":6},{"url":"/dataset/red-miniimagenet-20-label-noise","name":"Red MiniImageNet 20% label noise","full_name":"","num_papers_in_archive":6},{"url":"/dataset/red-miniimagenet-40-label-noise","name":"Red MiniImageNet 40% label noise","full_name":"","num_papers_in_archive":6},{"url":"/dataset/red-miniimagenet-80-label-noise","name":"Red MiniImageNet 80% label noise","full_name":"","num_papers_in_archive":6},{"url":"/dataset/coco-n-medium","name":"COCO-N Medium","full_name":"","num_papers_in_archive":1},{"url":"/dataset/coco-wan-medium-noise","name":"COCO-WAN (Medium noise)","full_name":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/document-text-classification","name":"Document Text Classification"},{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":143,"tagged_in_all":249,"items":[{"url":"/paper/sharpness-aware-minimization-for-efficiently-1","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","date":"2020-10-03","arxiv_id":"2010.01412","repositories_listed":18,"syntology":{"n":20,"n_ran":8,"n_unverified":12,"n_pointer_only":6}},{"url":"/paper/co-teaching-robust-training-of-deep-neural","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","date":"2018-04-18","arxiv_id":"1804.06872","repositories_listed":5,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/protoformer-embedding-prototypes-for-1","title":"Protoformer: Embedding Prototypes for Transformers","date":"2022-06-25","arxiv_id":"2206.12710","repositories_listed":4,"syntology":null},{"url":"/paper/learning-with-noisy-labels-revisited-a-study-1","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","date":"2021-10-22","arxiv_id":"2110.12088","repositories_listed":4,"syntology":null},{"url":"/paper/open-set-label-noise-can-improve-robustness","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","date":"2021-06-21","arxiv_id":"2106.10891","repositories_listed":4,"syntology":{"n":29,"n_ran":17,"n_unverified":12,"n_pointer_only":29}},{"url":"/paper/normalized-loss-functions-for-deep-learning","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","date":"2020-06-24","arxiv_id":"2006.13554","repositories_listed":4,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/confident-learning-estimating-uncertainty-in","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","date":"2019-10-31","arxiv_id":"1911.00068","repositories_listed":4,"syntology":{"n":29,"n_ran":4,"n_unverified":25,"n_pointer_only":3}},{"url":"/paper/symmetric-cross-entropy-for-robust-learning","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","date":"2019-08-16","arxiv_id":"1908.06112","repositories_listed":4,"syntology":null},{"url":"/paper/generalized-cross-entropy-loss-for-training","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","date":"2018-05-20","arxiv_id":"1805.07836","repositories_listed":4,"syntology":null},{"url":"/paper/probabilistic-end-to-end-noise-correction-for","title":"Probabilistic End-to-end Noise Correction for Learning with Noisy Labels","date":"2019-03-19","arxiv_id":"1903.07788","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/how-does-disagreement-help-generalization","title":"How does Disagreement Help Generalization against Label Corruption?","date":"2019-01-14","arxiv_id":"1901.04215","repositories_listed":3,"syntology":null},{"url":"/paper/dimensionality-driven-learning-with-noisy","title":"Dimensionality-Driven Learning with Noisy Labels","date":"2018-06-07","arxiv_id":"1806.02612","repositories_listed":3,"syntology":null},{"url":"/paper/mitigating-label-noise-on-graph-via","title":"Mitigating Label Noise on Graph via Topological Sample Selection","date":"2024-03-04","arxiv_id":"2403.01942","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/combining-distance-to-class-centroids-and","title":"Learning with Noisy Labels through Learnable Weighting and Centroid Similarity","date":"2023-03-16","arxiv_id":"2303.09470","repositories_listed":2,"syntology":null},{"url":"/paper/from-noisy-prediction-to-true-label-noisy","title":"From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model","date":"2022-05-02","arxiv_id":"2205.00690","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_unverified":7,"n_pointer_only":6}},{"url":"/paper/co-correcting-noise-tolerant-medical-image","title":"Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction","date":"2021-09-11","arxiv_id":"2109.05159","repositories_listed":2,"syntology":null},{"url":"/paper/clusterability-as-an-alternative-to-anchor","title":"Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels","date":"2021-02-10","arxiv_id":"2102.05291","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/when-optimizing-f-divergence-is-robust-with-1","title":"When Optimizing $f$-divergence is Robust with Label Noise","date":"2020-11-07","arxiv_id":"2011.03687","repositories_listed":2,"syntology":null},{"url":"/paper/early-learning-regularization-prevents","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","date":"2020-06-30","arxiv_id":"2007.00151","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/combating-noisy-labels-by-agreement-a-joint","title":"Combating noisy labels by agreement: A joint training method with co-regularization","date":"2020-03-05","arxiv_id":"2003.02752","repositories_listed":2,"syntology":null},{"url":"/paper/dividemix-learning-with-noisy-labels-as-semi-1","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","date":"2020-02-18","arxiv_id":"2002.07394","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/peer-loss-functions-learning-from-noisy","title":"Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates","date":"2019-10-08","arxiv_id":"1910.03231","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/l_dmi-an-information-theoretic-noise-robust","title":"L_DMI: An Information-theoretic Noise-robust Loss Function","date":"2019-09-08","arxiv_id":"1909.03388","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/making-deep-neural-networks-robust-to-label","title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","date":"2016-09-13","arxiv_id":"1609.03683","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/on-the-role-of-label-noise-in-the-feature","title":"On the Role of Label Noise in the Feature Learning Process","date":"2025-05-25","arxiv_id":"2505.18909","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/detect-and-correct-a-selective-noise","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","date":"2025-05-19","arxiv_id":"2505.13342","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-video-based-driver-activity","title":"Exploring Video-Based Driver Activity Recognition under Noisy Labels","date":"2025-04-16","arxiv_id":"2504.11966","repositories_listed":1,"syntology":null},{"url":"/paper/early-stopping-against-label-noise-without","title":"Early Stopping Against Label Noise Without Validation Data","date":"2025-02-11","arxiv_id":"2502.07551","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-open-world-noisy-data-via-class","title":"Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space","date":"2025-01-19","arxiv_id":"2501.11053","repositories_listed":1,"syntology":null},{"url":"/paper/psscl-a-progressive-sample-selection","title":"PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels","date":"2024-12-18","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}