Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/subeeshvasu/Awesome-Learning-with-Label-Noise

A curated list of resources for Learning with Noisy Labels
https://github.com/subeeshvasu/Awesome-Learning-with-Label-Noise

List: Awesome-Learning-with-Label-Noise

deep-neural-networks label-noise noisy-data noisy-labels robust-learning unreliable-labels

Last synced: 9 days ago
JSON representation

A curated list of resources for Learning with Noisy Labels

Awesome Lists containing this project

README 

        


    
Awesome Learning with Noisy Labels


    




    A curated list of resources for Learning with Noisy Labels



---



- [Learning-with-Label-Noise](#learning-with-label-noise)

  - [Papers & Code](#papers--code)

  - [Survey](#survey)

  - [Github](#github)

  - [Others](#others)

  - [Acknowledgements](#acknowledgements)



---



## Papers & Code



* 2008-NIPS - Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. [[Paper]](https://papers.nips.cc/paper/3644-whose-vote-should-count-more-optimal-integration-of-labels-from-labelers-of-unknown-expertise) [[Code]](https://github.com/notani/python-glad)



* 2009-ICML - Supervised learning from multiple experts: whom to trust when everyone lies a bit. [[Paper]](http://facweb.cti.depaul.edu/research/vc/seminar/Paper/37.pdf)



* 2011-NIPS - Bayesian Bias Mitigation for Crowdsourcing. [[Paper]](https://papers.nips.cc/paper/4311-bayesian-bias-mitigation-for-crowdsourcing)



* 2012-ICML - Learning to Label Aerial Images from Noisy Data. [[Paper]](https://www.cs.toronto.edu/~hinton/absps/noisy_maps.pdf)



* 2013-NIPS - Learning with Multiple Labels. [[Paper]](https://papers.nips.cc/paper/2234-learning-with-multiple-labels.pdf)



* 2013-NIPS - Learning with Noisy Labels. [[Paper]](https://papers.nips.cc/paper/5073-learning-with-noisy-labels.pdf) [[Code]](https://github.com/jamie2017/LearningWithNoisyLabels)



* 2014-ML - Learning from multiple annotators with varying expertise. [[Paper]](https://link.springer.com/article/10.1007/s10994-013-5412-1)



* 2014 - A Comprehensive Introduction to Label Noise. [[Paper]](https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-10.pdf)



* 2014 - Learning from Noisy Labels with Deep Neural Networks. [[Paper]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.749.1795&rep=rep1&type=pdf)



* 2015-ICLR_W - Training Convolutional Networks with Noisy Labels. [[Paper]](https://arxiv.org/abs/1406.2080) [[Code]](https://github.com/tesatory/convnet-noisy)



* 2015-CVPR - Learning from Massive Noisy Labeled Data for Image Classification. [[Paper]](http://www.ee.cuhk.edu.hk/~xgwang/papers/xiaoXYHWcvpr15.pdf) [[Code]](https://github.com/Cysu/noisy_label)



* 2015-CVPR - Visual recognition by learning from web data: A weakly supervised domain generalization approach. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2015/papers/Niu_Visual_Recognition_by_2015_CVPR_paper.pdf) [[Code]](https://wenli-vision.github.io/)



* 2015-CVPR - Training Deep Neural Networks on Noisy Labels with Bootstrapping. [[Paper]](https://arxiv.org/abs/1412.6596) [[Loss-Code-Unofficial-1]](https://github.com/edufonseca/icassp19/blob/master/losses.py) [[Loss-Code-Unofficial-2]](https://github.com/giorgiop/loss-correction/blob/master/loss.py) [[Code-Keras]](https://github.com/dr-darryl-wright/Noisy-Labels-with-Bootstrapping)



* 2015-ICCV - Webly supervised learning of convolutional networks. [[Paper]](http://openaccess.thecvf.com/content_iccv_2015/papers/Chen_Webly_Supervised_Learning_ICCV_2015_paper.pdf) [[Project Pagee]](http://xinleic.xyz/web.html)



* 2015-TPAMI - Classification with noisy labels by importance reweighting. [[Paper]](https://arxiv.org/pdf/1411.7718.pdf) [[Code]](https://github.com/xiaoboxia/Classification-with-noisy-labels-by-importance-reweighting)



* 2015-NIPS - Learning with Symmetric Label Noise: The Importance of Being Unhinged. [[Paper]](https://arxiv.org/abs/1505.07634) [[Loss-Code-Unofficial]](https://github.com/giorgiop/loss-correction/blob/master/loss.py)



* 2015-Arxiv - Making Risk Minimization Tolerant to Label Noise. [[Paper]](https://arxiv.org/abs/1403.3610)



* 2015 - Learning Discriminative Reconstructions for Unsupervised Outlier Removal. [[Paper]](https://www.ganghua.org/publication/ICCV15b.pdf) [[Code]](https://github.com/ClearMoonlight/SoCG_2019/tree/master/DRAE)



* 2015-TNLS - Rboost: label noise-robust boosting algorithm based on a nonconvex loss function and the numerically stable base learners. [[Paper]](https://ieeexplore.ieee.org/document/7273923)



* 2016-AAAI - Robust semi-supervised learning through label aggregation. [[Paper]](https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12312)



* 2016-ICLR - Auxiliary Image Regularization for Deep CNNs with Noisy Labels. [[Paper]](https://arxiv.org/abs/1511.07069) [[Code]](https://github.com/azadis/AIR)



* 2016-CVPR - Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels. [[Paper]](https://arxiv.org/abs/1512.06974) [[Code]](https://github.com/imisra/latent-noise-icnm)



* 2016-ICML - Loss factorization, weakly supervised learning and label noise robustness. [[Paper]](http://www.jmlr.org/proceedings/papers/v48/patrini16.pdf)



* 2016-RL - On the convergence of a family of robust losses for stochastic gradient descent. [[Paper]](https://arxiv.org/abs/1605.01623)



* 2016-NC - Noise detection in the Meta-Learning Level. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0925231215005482) [[Additional information]](https://github.com/lpfgarcia/m2n)



* 2016-ECCV - The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition. [[Paper]](https://arxiv.org/pdf/1511.06789) [[Project Page]](https://github.com/google/goldfinch)



* 2016-ICASSP - Training deep neural-networks based on unreliable labels. [[Paper]](http://ieeexplore.ieee.org/document/7472164/) [[Poster]](https://alanbekker.files.wordpress.com/2016/03/icassp_poster.pdf) [[Code-Unofficial]](https://github.com/Ryo-Ito/Noisy-Labels-Neural-Network)



* 2016-ICDM - Learning deep networks from noisy labels with dropout regularization. [[Paper]](https://arxiv.org/abs/1705.03419) [[Code]](https://github.com/ijindal/Noisy_Dropout_regularization)



* 2016-KBS - A robust multi-class AdaBoost algorithm for mislabeled noisy data. [[Paper]](https://dl.acm.org/doi/10.1016/j.knosys.2016.03.024)



* 2017-AAAI - Robust Loss Functions under Label Noise for Deep Neural Networks. [[Paper]](https://arxiv.org/abs/1712.09482)



* 2017-PAKDD - On the Robustness of Decision Tree Learning under Label Noise. [[Paper]](https://arxiv.org/pdf/1605.06296.pdf)



* 2017-ICLR - Training deep neural-networks using a noise adaptation layer. [[Paper]](https://openreview.net/forum?id=H12GRgcxg) [[Code]](https://github.com/udibr/noisy_labels)



* 2017-ICLR - Who Said What: Modeling Individual Labelers Improves Classification. [[Paper]](https://arxiv.org/abs/1703.08774) [[Code]](https://github.com/seunghyukcho/doctornet-pytorch)



* 2017-CVPR - Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Patrini_Making_Deep_Neural_CVPR_2017_paper.html) [[Code]](https://github.com/giorgiop/loss-correction)



* 2017-CVPR - Learning From Noisy Large-Scale Datasets With Minimal Supervision. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2017/html/Veit_Learning_From_Noisy_CVPR_2017_paper.html)



* 2017-CVPR - Lean crowdsourcing: Combining humans and machines in an online system. [[Paper]](https://ieeexplore.ieee.org/document/8100130) [[Code]](https://github.com/sbranson/online_crowdsourcing)



* 2017-CVPR - Attend in groups: a weakly-supervised deep learning framework for learning from web data. [[Paper]](https://arxiv.org/abs/1611.09960) [[Code]](https://github.com/bohanzhuang/Attend-in-Groups-a-Weakly-supervised-Deep-Learning-Framework-for-Learning-from-Web-Data)



* 2017-ICML - Robust Probabilistic Modeling with Bayesian Data Reweighting. [[Paper]](https://arxiv.org/abs/1606.03860) [[Code]](https://github.com/yixinwang/robust-rpm-public)



* 2017-ICCV - Learning From Noisy Labels With Distillation. [[Paper]](openaccess.thecvf.com/content_iccv_2017/html/Li_Learning_From_Noisy_ICCV_2017_paper.html) [[Code]](https://github.com/raingo/yfcc100m-entity)



* 2017-NIPS - Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks. [[Paper]](https://papers.nips.cc/paper/7143-toward-robustness-against-label-noise-in-training-deep-discriminative-neural-networks.pdf)



* 2017-NIPS - Active bias: Training more accurate neural networks by emphasizing high variance samples. [[Paper]](https://arxiv.org/abs/1704.07433) [[Code]](https://github.com/songhwanjun/ActiveBias)



* 2017-NIPS - Decoupling" when to update" from" how to update". [[Paper]](https://arxiv.org/abs/1706.02613) [[Code]](https://github.com/emalach/UpdateByDisagreement)



* 2017-IEEE-TIFS - A Light CNN for Deep Face Representation with Noisy Labels. [[Paper]](https://arxiv.org/abs/1511.02683) [[Code-Pytorch]](https://github.com/AlfredXiangWu/LightCNN) [[Code-Keras]](https://github.com/AlfredXiangWu/face_verification_experiment) [[Code-Tensorflow]](https://github.com/yxu0611/Tensorflow-implementation-of-LCNN)



* 2017-TNLS - Improving Crowdsourced Label Quality Using Noise Correction. [[Paper]](https://ieeexplore.ieee.org/document/7885126)



* 2017-ML - Learning to Learn from Weak Supervision by Full Supervision. [[Paper]](https://arxiv.org/abs/1711.11383) [[Code]](https://github.com/krayush07/learn-by-weak-supervision)



* 2017-ML - Avoiding your teacher's mistakes: Training neural networks with controlled weak supervision. [[Paper]](https://arxiv.org/abs/1711.00313)



* 2017-Arxiv - Deep Learning is Robust to Massive Label Noise. [[Paper]](https://arxiv.org/abs/1705.10694)



* 2017-Arxiv - Fidelity-weighted learning. [[Paper]](https://arxiv.org/pdf/1711.02799)



* 2017 - Self-Error-Correcting Convolutional Neural Network for Learning with Noisy Labels. [[Paper]](https://ieeexplore.ieee.org/document/7961730)



* 2017-Arxiv - Learning with confident examples: Rank pruning for robust classification with noisy labels. [[Paper]](https://arxiv.org/abs/1705.01936) [[Code]](https://github.com/cgnorthcutt/rankpruning)



* 2017-Arxiv - Regularizing neural networks by penalizing confident output distributions. [[Paper]](https://arxiv.org/abs/1701.06548)



* 2017 - Learning with Auxiliary Less-Noisy Labels. [[Paper]](https://ieeexplore.ieee.org/document/7448430)



* 2018-AAAI - Deep learning from crowds. [[Paper]](https://arxiv.org/abs/1709.01779)



* 2018-ICLR - mixup: Beyond Empirical Risk Minimization. [[Paper]](https://arxiv.org/abs/1710.09412) [[Code]](https://github.com/facebookresearch/mixup-cifar10)



* 2018-ICLR - Learning From Noisy Singly-labeled Data. [[Paper]](https://openreview.net/forum?id=H1sUHgb0Z) [[Code]](https://https://github.com/khetan2/MBEM)



* 2018-ICLR_W - How Do Neural Networks Overcome Label Noise?. [[Paper]](https://openreview.net/forum?id=ryu4RYJPM)



* 2018-CVPR - CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018/html/Lee_CleanNet_Transfer_Learning_CVPR_2018_paper.html) [[Code]](https://github.com/kuanghuei/clean-net)



* 2018-CVPR - Joint Optimization Framework for Learning with Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018/html/Tanaka_Joint_Optimization_Framework_CVPR_2018_paper.html) [[Code]](https://github.com/DaikiTanaka-UT/JointOptimization) [[Code-Unofficial-Pytorch]](https://github.com/YU1ut/JointOptimization)



* 2018-CVPR - Iterative Learning with Open-set Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Iterative_Learning_With_CVPR_2018_paper.html) [[Code]](https://github.com/YisenWang/Iterative_learning)



* 2018-ICML - MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels. [[Paper]](https://arxiv.org/abs/1712.05055) [[Code]](https://github.com/google/mentornet)



* 2018-ICML - Learning to Reweight Examples for Robust Deep Learning. [[Paper]](https://arxiv.org/abs/1803.09050) [[Code]](https://github.com/uber-research/learning-to-reweight-examples) [[Code-Unofficial-PyTorch]](https://github.com/danieltan07/learning-to-reweight-examples)



* 2018-ICML - Dimensionality-Driven Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/1806.02612) [[Code]](https://github.com/xingjunm/dimensionality-driven-learning)



* 2018-ECCV - CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images. [[Paper]](http://openaccess.thecvf.com/content_ECCV_2018/html/Sheng_Guo_CurriculumNet_Learning_from_ECCV_2018_paper.html) [[Code]](https://github.com/guoshengcv/CurriculumNet)



* 2018-ECCV - Deep Bilevel Learning. [[Paper]](https://arxiv.org/abs/1809.01465) [[Code]](https://github.com/sjenni/DeepBilevel)



* 2018-ECCV - Learning with Biased Complementary Labels. [[Paper]](https://eccv2018.org/openaccess/content_ECCV_2018/papers/Xiyu_Yu_Learning_with_Biased_ECCV_2018_paper.pdf) [[Code]](https://tongliang-liu.github.io/code.html)



* 2018-ISBI - Training a neural network based on unreliable human annotation of medical images. [[Paper]](http://www.eng.biu.ac.il/goldbej/files/2018/01/ISBI_2018_Yair.pdf)



* 2018-WACV - Iterative Cross Learning on Noisy Labels. [[Paper]](https://ieeexplore.ieee.org/document/8354192)



* 2018-WACV - A semi-supervised two-stage approach to learning from noisy labels. [[Paper]](https://arxiv.org/abs/1802.02679)



* 2018-NIPS - Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. [[Paper]](https://papers.nips.cc/paper/8072-co-teaching-robust-training-of-deep-neural-networks-with-extremely-noisy-labels.pdf) [[Code]](https://github.com/bhanML/Co-teaching)



* 2018-NIPS - Masking: A New Perspective of Noisy Supervision. [[Paper]](https://papers.nips.cc/paper/7825-masking-a-new-perspective-of-noisy-supervision.pdf) [[Code]](https://github.com/bhanML/Masking)



* 2018-NIPS - Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise. [[Paper]](https://papers.nips.cc/paper/8246-using-trusted-data-to-train-deep-networks-on-labels-corrupted-by-severe-noise) [[Code]](https://github.com/mmazeika/glc)



* 2018-NIPS - Robustness of conditional GANs to noisy labels. [[Paper]](https://arxiv.org/abs/1811.03205) [[Code]](https://github.com/POLane16/Robust-Conditional-GAN)



* 2018-NIPS - Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels. [[Paper]](https://papers.nips.cc/paper/8094-generalized-cross-entropy-loss-for-training-deep-neural-networks-with-noisy-labels.pdf) [[Loss-Code-Unofficial]](https://github.com/edufonseca/icassp19/blob/master/losses.py)



* 2018-TIP - Deep learning from noisy image labels with quality embedding. [[Paper]](https://arxiv.org/abs/1711.00583)



* 2018-TNLS - Progressive Stochastic Learning for Noisy Labels. [[Paper]](https://ieeexplore.ieee.org/document/8281022)



* 2018 - Multiclass Learning with Partially Corrupted Labels. [[Paper]](https://ieeexplore.ieee.org/abstract/document/7929355)



* 2018-Arxiv- Improving Multi-Person Pose Estimation using Label Correction. [[Paper]](https://arxiv.org/pdf/1811.03331.pdf)



* 2018 - Robust Determinantal Generative Classifier for Noisy Labels and Adversarial Attacks. [[Paper]](https://openreview.net/forum?id=rkle3i09K7)



* 2019-AAAI - Safeguarded Dynamic Label Regression for Generalized Noisy Supervision. [[Paper]](https://sunarker.github.io/temp/AAAI2019_Dynamic_Label_Regression_for_Noisy_Supervision.pdf) [[Code]](https://github.com/Sunarker/Safeguarded-Dynamic-Label-Regression-for-Noisy-Supervision) [[Slides]](https://sunarker.github.io/temp/AAAI2019_Presentation.pdf) [[Poster]](https://sunarker.github.io/temp/AAAI2019_Poster.pdf)



* 2019-ICLR_W - SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels.[[Paper]](https://arxiv.org/pdf/1805.09622.pdf) [[Code]](https://github.com/orlitany/SOSELETO)



* 2019-CVPR - Learning From Noisy Labels by Regularized Estimation of Annotator Confusion. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/html/Tanno_Learning_From_Noisy_Labels_by_Regularized_Estimation_of_Annotator_Confusion_CVPR_2019_paper.html)



* 2019-CVPR - Learning to Learn from Noisy Labeled Data. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Learning_to_Learn_From_Noisy_Labeled_Data_CVPR_2019_paper.pdf) [[Code]](https://github.com/LiJunnan1992/MLNT)



* 2019-CVPR - Learning a Deep ConvNet for Multi-label Classification with Partial Labels. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Durand_Learning_a_Deep_ConvNet_for_Multi-Label_Classification_With_Partial_Labels_CVPR_2019_paper.html)



* 2019-CVPR - Label-Noise Robust Generative Adversarial Networks. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Kaneko_Label-Noise_Robust_Generative_Adversarial_Networks_CVPR_2019_paper.html) [[Code]](https://github.com/takuhirok/rGAN)



* 2019-CVPR - Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Tanno_Learning_From_Noisy_Labels_by_Regularized_Estimation_of_Annotator_Confusion_CVPR_2019_paper.html) [[Code]](https://rt416.github.io/pdf/trace_codes.pdf)



* 2019-CVPR - Probabilistic End-to-end Noise Correction for Learning with Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Yi_Probabilistic_End-To-End_Noise_Correction_for_Learning_With_Noisy_Labels_CVPR_2019_paper.html) [[Code]](https://github.com/yikun2019/PENCIL)



* 2019-CVPR - Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhong_Graph_Convolutional_Label_Noise_Cleaner_Train_a_Plug-And-Play_Action_Classifier_CVPR_2019_paper.html) [[Code]](https://github.com/jx-zhong-for-academic-purpose/GCN-Anomaly-Detection)



* 2019-CVPR - Improving Semantic Segmentation via Video Propagation and Label Relaxation. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Zhu_Improving_Semantic_Segmentation_via_Video_Propagation_and_Label_Relaxation_CVPR_2019_paper.html) [[Code]](https://github.com/NVIDIA/semantic-segmentation)



* 2019-CVPR - Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Acuna_Devil_Is_in_the_Edges_Learning_Semantic_Boundaries_From_Noisy_CVPR_2019_paper.html) [[Code]](https://github.com/nv-tlabs/STEAL) [[Project-page]](https://nv-tlabs.github.io/STEAL/)



* 2019-CVPR - Noise-Tolerant Paradigm for Training Face Recognition CNNs. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/html/Hu_Noise-Tolerant_Paradigm_for_Training_Face_Recognition_CNNs_CVPR_2019_paper.html) [[Code]](https://github.com/huangyangyu/NoiseFace)



* 2019-CVPR - A Nonlinear, Noise-aware, Quasi-clustering Approach to Learning Deep CNNs from Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_CVPRW_2019/papers/Deep%20Vision%20Workshop/Jindal_A_Nonlinear_Noise-aware_Quasi-clustering_Approach_to_Learning_Deep_CNNs_from_CVPRW_2019_paper.pdf)



* 2019-IJCAI - Learning Sound Events from Webly Labeled Data. [[Paper]](https://www.ijcai.org/proceedings/2019/0384.pdf) [[Code]](https://github.com/anuragkr90/webly-labeled-sounds)



* 2019-ICML - Unsupervised Label Noise Modeling and Loss Correction. [[Paper]](https://arxiv.org/abs/1904.11238) [[Code]](https://github.com/PaulAlbert31/LabelNoiseCorrection)



* 2019-ICML - Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels. [[Paper]](http://proceedings.mlr.press/v97/chen19g.html) [[Code]](https://github.com/chenpf1025/noisy_label_understanding_utilizing)



* 2019-ICML - How does Disagreement Help Generalization against Label Corruption?. [[Paper]](https://arxiv.org/abs/1901.04215) [[Code]](https://github.com/bhanML/coteaching_plus)



* 2019-ICML - Using Pre-Training Can Improve Model Robustness and Uncertainty. [[Paper]](https://arxiv.org/abs/1901.09960) [[Code]](https://github.com/hendrycks/pre-training)



* 2019-ICML - On Symmetric Losses for Learning from Corrupted Labels. [[Paper]](https://arxiv.org/abs/1901.09314) [[Poster]](https://nolfwin.github.io/assets/poster/ICML2019_Symloss_poster.pdf) [[Slides]](https://nolfwin.github.io/assets/slides/ICML2019_Symloss_slides.pdf) [[Code]](https://github.com/nolfwin/symloss-ber-auc)



* 2019-ICML - Combating Label Noise in Deep Learning Using Abstention. [[Paper]](https://arxiv.org/abs/1905.10964) [[Code]](https://github.com/thulas/dac-label-noise)



* 2019-ICML - SELFIE: Refurbishing unclean samples for robust deep learning. [[Paper]](http://proceedings.mlr.press/v97/song19b.html) [[Code]](https://github.com/kaist-dmlab/SELFIE)



* 2019-ICASSP - Learning Sound Event Classifiers from Web Audio with Noisy Labels. [[Paper]](https://arxiv.org/abs/1901.01189) [[Code]](https://github.com/edufonseca/icassp19)



* 2019-TGRS - Hyperspectral Image Classification in the Presence of Noisy Labels. [[Paper]](https://arxiv.org/abs/1809.04212) [[Code]](https://github.com/junjun-jiang/RLPA)



* 2019-ICCV - NLNL: Negative Learning for Noisy Labels. [[Paper]](https://arxiv.org/abs/1908.07387) [[Code]](https://github.com/ydkim1293/NLNL-Negative-Learning-for-Noisy-Labels)



* 2019-ICCV - Symmetric Cross Entropy for Robust Learning With Noisy Labels. [[Paper]](https://arxiv.org/abs/1908.06112) [[Code]](https://github.com/YisenWang/symmetric_cross_entropy_for_noisy_labels)



* 2019-ICCV - Co-Mining: Deep Face Recognition With Noisy Labels.[[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Co-Mining_Deep_Face_Recognition_With_Noisy_Labels_ICCV_2019_paper.html)



* 2019-ICCV - O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks.[[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_O2U-Net_A_Simple_Noisy_Label_Detection_Approach_for_Deep_Neural_ICCV_2019_paper.html) [[Code]](https://github.com/hjimce/O2U-Net)



* 2019-ICCV - Deep Self-Learning From Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/html/Han_Deep_Self-Learning_From_Noisy_Labels_ICCV_2019_paper.html) [[Code]](https://github.com/sarsbug/SMP)



* 2019-ICCV_W - Photometric Transformer Networks and Label Adjustment for Breast Density Prediction. [[Paper]](https://arxiv.org/abs/1905.02906)



* 2019-NIPS - Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting.[[Paper]](https://arxiv.org/abs/1902.07379) [[Code]](https://github.com/xjtushujun/meta-weight-net)



* 2019-TPAMI - Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification. [[Paper]](https://arxiv.org/abs/1811.00700)



* 2019-ISBI - Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification. [[Paper]](https://arxiv.org/abs/1901.07759)



* 2019-AISTATS - Two-temperature logistic regression based on the Tsallis divergence. [[Paper]](https://arxiv.org/abs/1705.07210)



* 2019-NIPS - Robust bi-tempered logistic loss based on Bregman divergences. [[Paper]](https://arxiv.org/abs/1906.03361) [[Blog]](https://ai.googleblog.com/2019/08/bi-tempered-logistic-loss-for-training.html) [[Code]](https://github.com/google/bi-tempered-loss) [[Demo]](https://google.github.io/bi-tempered-loss/)



* 2019-NIPS - Are Anchor Points Really Indispensable in Label-Noise Learning?. [[Paper]](https://papers.nips.cc/paper/8908-are-anchor-points-really-indispensable-in-label-noise-learning.pdf) [[Code]](https://github.com/xiaoboxia/T-Revision)



* 2019-NIPS - Noise-tolerant fair classification. [[Paper]](https://papers.nips.cc/paper/8322-noise-tolerant-fair-classification) [[Code]](https://github.com/AIasd/noise_fairlearn)



* 2019-NIPS - Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels. [[Paper]](https://papers.nips.cc/paper/8378-correlated-uncertainty-for-learning-dense-correspondences-from-noisy-labels)



* 2019-NIPS - Combinatorial Inference against Label Noise. [[Paper]](https://papers.nips.cc/paper/8401-combinatorial-inference-against-label-noise) [[Code]](https://github.com/snow12345/Combinatorial_Classification)



* 2019-NIPS - L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise. [[Paper]](https://papers.nips.cc/paper/8853-l_dmi-a-novel-information-theoretic-loss-function-for-training-deep-nets-robust-to-label-noise) [[Code]](https://github.com/Newbeeer/L_DMI)



* 2019-Arxiv - ChoiceNet: Robust Learning by Revealing Output Correlations. [[Paper]]([https://openreview.net/forum?id=S1MQ6jCcK7](https://openaccess.thecvf.com/content_CVPR_2020/html/Choi_Task_Agnostic_Robust_Learning_on_Corrupt_Outputs_by_Correlation-Guided_Mixture_CVPR_2020_paper.html))



* 2019-Arxiv - Robust Learning Under Label Noise With Iterative Noise-Filtering. [[Paper]](https://arxiv.org/abs/1906.00216)



* 2019-Arxiv - IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters. [[Paper]](https://arxiv.org/abs/1903.12141) [[Project page]](https://github.com/XinshaoAmosWang/Improving-Mean-Absolute-Error-against-CCE)



* 2019-Arxiv - Confident Learning: Estimating Uncertainty in Dataset Labels. [[Paper]](https://arxiv.org/abs/1911.00068) [[Code]](https://github.com/cgnorthcutt/cleanlab)



* 2019-Arxiv - Derivative Manipulation for General Example Weighting. [[Paper]](https://arxiv.org/abs/1905.11233) [[Code]](https://github.com/XinshaoAmosWang/DerivativeManipulation)



* 2020-ICPR - Towards Robust Learning with Different Label Noise Distributions. [[Paper]](https://arxiv.org/abs/1912.08741) [[Code]](https://git.io/JJ0PV)



* 2020-AAAI - Reinforcement Learning with Perturbed Rewards. [[Paper]](https://arxiv.org/abs/1810.01032) [[Code]](https://github.com/wangjksjtu/rl-perturbed-reward)



* 2020-AAAI - Less Is Better: Unweighted Data Subsampling via Influence Function. [[Paper]](https://arxiv.org/abs/1912.01321) [[Code]](https://github.com/RyanWangZf/Influence_Subsampling)



* 2020-AAAI - Label Error Correction and Generation Through Label Relationships. [[Paper]](https://www.ecse.rpi.edu/~cvrl/Publication/pdf/Cui2020.pdf)



* 2020-AAAI - Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data. [[Paper]](http://people.cs.vt.edu/~ctlu/Publication/2020/AAAI-ZhangX-8567-Proceedings.pdf)



* 2020-AAAI - Coupled-view Deep Classifier Learning from Multiple Noisy Annotators. [[Paper]](https://aaai.org/Papers/AAAI/2020GB/AAAI-LiS.504.pdf)



* 2020-AAAI - Partial Multi-label Learning with Noisy Label Identification. [[Paper]](https://aaai.org/Papers/AAAI/2020GB/AAAI-LiS.504.pdf)



* 2020-WACV - A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels. [[Paper]](http://openaccess.thecvf.com/content_WACV_2020/html/Mandal_A_Novel_Self-Supervised_Re-labeling_Approach_for_Training_with_Noisy_Labels_WACV_2020_paper.html)



* 2020-WACV - Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision. [[Paper]](http://openaccess.thecvf.com/content_WACV_2020/html/Mangalam_Disentangling_Human_Dynamics_for_Pedestrian_Locomotion_Forecasting_with_Noisy_Supervision_WACV_2020_paper.html)



* 2020-WACV - Learning from Noisy Labels via Discrepant Collaborative Training. [[Paper]](http://openaccess.thecvf.com/content_WACV_2020/html/Han_Learning_from_Noisy_Labels_via_Discrepant_Collaborative_Training_WACV_2020_paper.html)



* 2020-ICLR - SELF: Learning to Filter Noisy Labels with Self-Ensembling. [[Paper]](https://arxiv.org/abs/1910.01842)



* 2020-ICLR - DivideMix: Learning with Noisy Labels as Semi-supervised Learning. [[Paper]](https://arxiv.org/abs/2002.07394) [[Code]](https://github.com/LiJunnan1992/DivideMix)



* 2020-ICLR - Can gradient clipping mitigate label noise?. [[Paper]](https://openreview.net/pdf?id=rklB76EKPr) [[Code]](https://github.com/dmizr/phuber)



* 2020-ICLR - Curriculum Loss: Robust Learning and Generalization against Label Corruption. [[Paper]](https://arxiv.org/abs/1905.10045)



* 2020-ICLR - Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee. [[Paper]](https://arxiv.org/abs/1905.11368)



* 2020-ICLR - Learning from Rules Generalizing Labeled Exemplars. [[Paper]](https://openreview.net/pdf?id=SkeuexBtDr) [[Code]](https://github.com/awasthiabhijeet/Learning-From-Rules)



* 2020-ICLR - Robust training with ensemble consensus. [[Paper]](https://openreview.net/forum?id=ryxOUTVYDH) [[Code]](https://github.com/jisoolee0123/Robust-training-with-ensemble-consensus)



* 2020-CVPR - Combating noisy labels by agreement: A joint training method with co-regularization. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Wei_Combating_Noisy_Labels_by_Agreement_A_Joint_Training_Method_with_CVPR_2020_paper.html) [[Code]](https://github.com/hongxin001/JoCoR)



* 2020-CVPR - Distilling Effective Supervision From Severe Label Noise. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Distilling_Effective_Supervision_From_Severe_Label_Noise_CVPR_2020_paper.html) [[Code]](https://github.com/google-research/google-research/tree/master/ieg)



* 2020-CVPR - Learning From Noisy Anchors for One-Stage Object Detection. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Li_Learning_From_Noisy_Anchors_for_One-Stage_Object_Detection_CVPR_2020_paper.html) [[Code]](https://github.com/henrylee2570/NoisyAnchor)



* 2020-CVPR - Self-Training With Noisy Student Improves ImageNet Classification. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Xie_Self-Training_With_Noisy_Student_Improves_ImageNet_Classification_CVPR_2020_paper.html) [[Code]](https://github.com/google-research/noisystudent)



* 2020-CVPR - Noise Robust Generative Adversarial Networks. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Kaneko_Noise_Robust_Generative_Adversarial_Networks_CVPR_2020_paper.html) [[Code]](https://github.com/takuhirok/NR-GAN/)



* 2020-CVPR - Noise-Aware Fully Webly Supervised Object Detection. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Shen_Noise-Aware_Fully_Webly_Supervised_Object_Detection_CVPR_2020_paper.html) [[Code]](https://github.com/shenyunhang/NA-fWebSOD)



* 2020-CVPR - Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition. [[Paper]](http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Global-Local_GCN_Large-Scale_Label_Noise_Cleansing_for_Face_Recognition_CVPR_2020_paper.html)



* 2020-CVPR - Training Noise-Robust Deep Neural Networks via Meta-Learning. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_Training_Noise-Robust_Deep_Neural_Networks_via_Meta-Learning_CVPR_2020_paper.pdf) [[Code]](https://github.com/ZhenWang-PhD/Training-Noise-Robust-Deep-Neural-Networks-via-Meta-Learning)



* 2020-CVPR - Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2020/html/Choi_Task_Agnostic_Robust_Learning_on_Corrupt_Outputs_by_Correlation-Guided_Mixture_CVPR_2020_paper.html) [[code]](https://github.com/sjchoi86/choicenet)



* 2020-ICML - Learning with Bounded Instance-and Label-dependent Label Noise. [[Paper]](https://arxiv.org/abs/1709.03768) [[Matlab Code]](https://github.com/JiachengCheng96/Learning-with-bounded-instance-and-label-dependent-label-noise)



* 2020-ICML - Label-Noise Robust Domain Adaptation. [[Paper]](https://proceedings.icml.cc/static/paper_files/icml/2020/1942-Paper.pdf)



* 2020-ICML - LTF: A Label Transformation Framework for Correcting Label Shift. [[Papeer]](https://proceedings.icml.cc/static/paper_files/icml/2020/1262-Paper.pdf)



* 2020-ICML - Does label smoothing mitigate label noise?. [[Paper]](https://arxiv.org/abs/2003.02819)



* 2020-ICML - Error-Bounded Correction of Noisy Labels. [[Paper]](https://proceedings.icml.cc/static/paper_files/icml/2020/2506-Paper.pdf) [[Code]](https://github.com/pingqingsheng/LRT)



* 2020-ICML - Deep k-NN for Noisy Labels. [[Paper]](https://arxiv.org/abs/2004.12289)



* 2020-ICML - Searching to Exploit Memorization Effect in Learning from Noisy Labels. [[Paper]](https://arxiv.org/abs/1911.02377) [[Code]](https://github.com/AutoML-4Paradigm/S2E)



* 2020-ICML - Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels. [[Paper]](https://arxiv.org/abs/1911.09781) [[Code]](https://github.com/LJY-HY/MentorMix_pytorch)



* 2020-ICML - Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates. [[Paper]](https://arxiv.org/abs/1910.03231)



* 2020-ICML - Improving Generalization by Controlling Label-Noise Information in Neural Network Weights. [[Paper]](https://arxiv.org/abs/2002.07933) [[Code]](https://github.com/hrayrhar/limit-label-memorization)



* 2020-ICML - Training Binary Neural Networks through Learning with Noisy Supervision. [[Paperr]](https://proceedings.icml.cc/static/paper_files/icml/2020/181-Paper.pdf) [[Code]](https://github.com/zhaohui-yang/Binary-Neural-Networks)



* 2020-ICML - SIGUA: Forgetting May Make Learning with Noisy Labels More Robust. [[Paper]](https://proceedings.icml.cc/static/paper_files/icml/2020/705-Paper.pdf) [[Code]](https://github.com/bhanML/SIGUA)



* 2020-ICML - Normalized Loss Functions for Deep Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2006.13554) [[Code]](https://github.com/HanxunH/Active-Passive-Losses)



* 2020-ICML_W - How does Early Stopping Help Generalization against Label Noise?. [[Paper]](https://arxiv.org/abs/1911.08059)



* 2020-IJCAI - learning with Noise: Improving Distantly-Supervised Fine-grained Entity Typing via Automatic Relabeling. [[Paper]](https://www.ijcai.org/Proceedings/2020/0527.pdf)



* 2020-IJCAI - Can Cross Entropy Loss Be Robust to Label Noise?. [[Paper]](https://www.ijcai.org/Proceedings/2020/305)



* 2020-ECCV - Graph convolutional networks for learning with few clean and many noisy labels. [[Paper]](https://arxiv.org/abs/1910.00324) [[Code]](https://github.com/google-research/noisy-fewshot-learning)



* 2020-ECCV - Learning with Noisy Class Labels for Instance Segmentation. [[Paper]](http://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2062_ECCV_2020_paper.php) [[Code]](https://github.com/longrongyang/LNCIS)



* 2020-ECCV - Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection. [[Paper]](https://arxiv.org/abs/2007.12211) [[Code]](https://github.com/JingZhang617/Noise-aware-ABP-Saliency)



* 2020-ECCV - NoiseRank: Unsupervised Label Noise Reduction with Dependence Models. [[Paper]](https://arxiv.org/abs/2003.06729)



* 2020-ECCV - Weakly-Supervised Learning with Side Information for Noisy Labeled Images. [[Paper]](https://arxiv.org/abs/2008.11586)



* 2020-ECCV - Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces. [[Paper]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560715.pdf) [[Code]](https://github.com/deepinsight/insightface)



* 2020-TASLP - Audio Tagging by Cross Filtering Noisy Labels. [[Paper]](https://arxiv.org/abs/2007.08165)



* 2020-NIPS - Robust Optimization for Fairness with Noisy Protected Groups. [[Paper]](https://arxiv.org/pdf/2002.09343.pdf) [[Code]](https://github.com/wenshuoguo/robust-fairness-code)



* 2020-NIPS - A Topological Filter for Learning with Label Noise. [[Paper]](https://arxiv.org/pdf/2012.04835.pdf) [[Code]](https://github.com/pxiangwu/TopoFilter)



* 2020-NIPS - Self-Adaptive Training: beyond Empirical Risk Minimization. [[Paper]](https://arxiv.org/abs/2002.10319) [[Code]](https://github.com/LayneH/self-adaptive-training)



* 2020-NIPS - Parts-dependent Label Noise: Towards Instance-dependent Label Noise. [[Paper]](https://arxiv.org/abs/2006.07836)[[Code]](https://github.com/xiaoboxia/Part-dependent-label-noise)



* 2020-NIPS - Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning. [[Paper]](https://arxiv.org/abs/2006.07805)



* 2020-NIPS - Early-Learning Regularization Prevents Memorization of Noisy Labels. [[Paper]](https://arxiv.org/abs/2007.00151) [[Code]](https://github.com/shengliu66/ELR)



* 2020-NIPS - Disentangling Human Error from the Ground Truth in Segmentation of Medical Images. [[Paper]](https://arxiv.org/abs/2007.15963) [[Code]](https://github.com/moucheng2017/Learn_Noisy_Labels_Medical_Images)



* 2020-NIPS - Identifying Mislabeled Data using the Area Under the Margin Ranking. [[Paper]](https://arxiv.org/abs/2001.10528) [[Code]](https://github.com/Manuscrit/Area-Under-the-Margin-Ranking)



* 2020-NIPS - Coresets for Robust Training of Neural Networks against Noisy Labels. [[Paper]](https://proceedings.neurips.cc//paper/2020/hash/8493eeaccb772c0878f99d60a0bd2bb3-Abstract.html) [[Code]](https://github.com/snap-stanford/crust)



* 2020-IJCNN - Temporal Calibrated Regularization for Robust Noisy Label Learning. [[Paper]](https://arxiv.org/abs/2007.00240)



* 2020-MICCAI - Characterizing Label Errors: Confident Learning for Noisy-labeled Image Segmentation. [[Paper]](https://link.springer.com/chapter/10.1007/978-3-030-59710-8_70) [[Code]](https://github.com/502463708/Confident_Learning_for_Noisy-labeled_Medical_Image_Segmentation)



* 2020-ICPR - Meta Soft Label Generation for Noisy Labels. [[Paper]](https://arxiv.org/abs/2007.05836) [[Code]](https://github.com/gorkemalgan/MSLG_noisy_label)



* 2020-IJCV - Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation [[Paper]](https://arxiv.org/abs/2003.03773) [[Code]](https://github.com/layumi/Seg-Uncertainty)



* 2020-IEEEAccess - Limited Gradient Descent: Learning With Noisy Labels. [[Paper]](https://arxiv.org/abs/1811.08117)



* 2020-Arxiv - Multi-Class Classification from Noisy-Similarity-Labeled Data. [[Paper]](https://arxiv.org/abs/2002.06508)



* 2020-Arxiv - Learning Adaptive Loss for Robust Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2002.06482)



* 2020-Arxiv - Class2Simi: A New Perspective on Learning with Label Noise. [[Paper]](https://arxiv.org/abs/2006.07831)



* 2020-Arxiv - Confidence Scores Make Instance-dependent Label-noise Learning Possible. [[Paper]](https://arxiv.org/pdf/2001.03772.pdf) [[Code]](https://github.com/antoninbrthn/CSIDN)



* 2020-Arxiv - ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks. [[Paper]](https://arxiv.org/abs/2005.03788) [[Code]](https://github.com/XinshaoAmosWang/ProSelfLC)



* 2020-Arxiv - Learning from Noisy Labels with Noise Modeling Network. [[Paper]](https://arxiv.org/abs/2005.00596)



* 2020-Arxiv - ExpertNet: Adversarial Learning and Recovery Against Noisy Labels. [[Paper]](https://arxiv.org/abs/2007.05305)



* 2020-Arxiv - Noisy Labels Can Induce Good Representations. [[Paper]](https://arxiv.org/pdf/2012.12896.pdf)



* 2020-Arxiv - Contrast to Divide: self-supervised pre-training for learning with noisy labels. [[Paper]](https://openreview.net/forum?id=uB5x7Y2qsFR) [[Code]](https://github.com/ContrastToDivide/C2D)



* 2021- IEEE PAMI - Wasserstein Adversarial Regularization for Learning With Label Noise. [[Paper]](https://arxiv.org/abs/1904.03936v3, https://ieeexplore.ieee.org/document/9477020) [[Code]] (https://github.com/bbdamodaran/WAR)

*

* 2021-AAAI - Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2012.04193) [[Code]](https://github.com/chenpf1025/RobustnessAccuracy)



* 2021-AAAI - Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise. [[Paper]](https://arxiv.org/abs/2012.05458) [[Code]](https://github.com/chenpf1025/IDN)



* 2021-AAAI - Meta Label Correction for Noisy Label Learning. [[Paper]](https://www.microsoft.com/en-us/research/publication/meta-label-correction-for-noisy-label-learning/) [[Code]](https://github.com/microsoft/MLC)



* 2021-AAAI - From Label Smoothing to Label Relaxation. [[Paper]](https://www.aaai.org/AAAI21Papers/AAAI-2191.LienenJ.pdf) [[Code]](https://github.com/julilien/LabelRelaxation)



* 2021-AAAI - Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. [[Paper]](https://arxiv.org/abs/2101.05467)



* 2021-WACV - Do We Really Need Gold Samples for Sample Weighting Under Label Noise? [[Paper]](https://openaccess.thecvf.com/content/WACV2021/papers/Ghosh_Do_We_Really_Need_Gold_Samples_for_Sample_Weighting_Under_WACV_2021_paper.pdf) [[Code]](https://github.com/arghosh/RobustMW-Net)



* 2021-WACV - EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels. [[Paper]](https://arxiv.org/abs/2011.05704) [[Code]](https://github.com/ragavsachdeva/EvidentialMix) [[Blog]](https://ragavsachdeva.github.io/research/2020/evidentialmix/)



* 2021-CVPR - Improving Unsupervised Image Clustering With Robust Learning. [[Paper]](https://arxiv.org/abs/2012.11150) [[Code]](https://github.com/deu30303/RUC)



* 2021-CVPR - Multi-Objective Interpolation Training for Robustness to Label Noise. [[Paper]](https://arxiv.org/abs/2012.04462) [[Code]](https://git.io/JI40X)



* 2021-CVPR - Noise-resistant Deep Metric Learning with Ranking-based Instance Selection. [[Paper]](https://arxiv.org/abs/2103.16047) [[Code]](https://github.com/alibaba-edu/Ranking-based-Instance-Selection)



* 2021-CVPR - Augmentation Strategies for Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2103.02130) [[Code]](https://github.com/KentoNishi/Augmentation-for-LNL)



* 2021-CVPR - A Second-Order Approach to Learning with Instance-Dependent Label Noise. [[Paper]](https://arxiv.org/abs/2012.11854v2) [[Code]](https://github.com/UCSC-REAL/CAL)



* 2021-CVPR - Faster Meta Update Strategy for Noise-Robust Deep Learning. [[Paper]](https://github.com/youjiangxu/FaMUS/blob/main/paper/famus.pdf) [[Code]](https://github.com/youjiangxu/FaMUS)



* 2021-CVPR - Partially View-aligned Representation Learning with Noise-robust Contrastive Loss. [[Paper]](https://github.com/XLearning-SCU/2021-CVPR-MvCLN) [[Code]](https://github.com/XLearning-SCU/2021-CVPR-MvCLN)



* 2021-CVPR - Correlated Input-Dependent Label Noise in Large-Scale Image Classification. [[Paper]](https://arxiv.org/pdf/2105.10305v1.pdf)



* 2021-CVPR - Divergence Optimization for Noisy Universal Domain Adaptation. [[Paper]](https://arxiv.org/abs/2104.00246) [[Code]](https://github.com/YU1ut/Divergence-Optimization)



* 2021-CVPR - Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification. [[Paper]](https://arxiv.org/abs/2103.04618) [[Code]](https://github.com/FlyingRoastDuck/MetaCam_DSCE)



* 2021-CVPR - Jo-SRC: A Contrastive Approach for Combating Noisy Labels. [[Paper]](https://arxiv.org/abs/2103.13029) [[Code]](https://github.com/NUST-Machine-Intelligence-Laboratory/Jo-SRC)



* 2021-CVPR - Learning Cross-Modal Retrieval With Noisy Labels. [[Paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Hu_Learning_Cross-Modal_Retrieval_With_Noisy_Labels_CVPR_2021_paper.pdf)



* 2021-CVPR - Learning an Explicit Weighting Scheme for Adapting Complex HSI Noise. [[Paper]](http://gr.xjtu.edu.cn/documents/15788/0/11627.pdf/0b7e0225-2b81-0d1c-27d4-16a080235e37?t=1617536301666) [[Code]](https://github.com/xyrui/HWnet)



* 2021-CVPR - DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions. [[Paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Qu_DAT_Training_Deep_Networks_Robust_To_Label-Noise_by_Matching_the_CVPR_2021_paper.pdf)



* 2021-CVPR - Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation. [[Paper]](https://arxiv.org/abs/2104.00905) [[Code]](https://github.com/cvlab-yonsei/BANA)



* 2021-CVPR - Joint Negative and Positive Learning for Noisy Labels. [[Paper]](https://arxiv.org/abs/2104.06574) [[Code]](https://github.com/CQUEEN-lpy/JNPL)



* 2021-CVPR - DualGraph: A Graph-Based Method for Reasoning About Label Noise. [[Paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_DualGraph_A_Graph-Based_Method_for_Reasoning_About_Label_Noise_CVPR_2021_paper.pdf)



* 2021-CVPR - AutoDO: Robust AutoAugment for Biased Data With Label Noise via Scalable Probabilistic Implicit Differentiation. [[Paper]](https://arxiv.org/abs/2103.05863) [[Code]](https://github.com/gudovskiy/autodo)



* 2021-CVPRW - Contrastive Learning Improves Model Robustness Under Label Noise. [[Paper]](https://arxiv.org/pdf/2104.08984.pdf) [[Code]](https://github.com/arghosh/noisy_label_pretrain)



* 2021-CVPRW - Boosting Co-teaching with Compression Regularization for Label Noise. [[Paper]](https://arxiv.org/abs/2104.13766) [[Code]](https://github.com/yingyichen-cyy/Nested-Co-teaching)



* 2021-ICLR - Learning with Feature-Dependent Label Noise: A Progressive Approach. [[Paper]](https://openreview.net/pdf?id=ZPa2SyGcbwh) [[Code]](https://github.com/pxiangwu/PLC)



* 2021-ICLR - Robust early-learning: Hindering the memorization of noisy labels. [[Paper]](https://openreview.net/forum?id=Eql5b1_hTE4) [[Code]](https://github.com/xiaoboxia/CDR)



* 2021-ICLR - MoPro: Webly Supervised Learning with Momentum Prototypes. [[Paper]](https://openreview.net/forum?id=0-EYBhgw80y) [[Code]](https://github.com/salesforce/MoPro)



* 2021-TIP - Delving Deep into Label Smoothing. [[Paper]](http://mftp.mmcheng.net/Papers/21TIP-OLS.pdf) [[Code]](https://github.com/zhangchbin/OnlineLabelSmoothing)



* 2021-PAKDD - Memorization in Deep Neural Networks: Does the Loss Function Matter? [[Paper]](https://link.springer.com/chapter/10.1007/978-3-030-75765-6_11) [[Code]](https://github.com/dbp1994/masters_thesis_codes/tree/main/memorization_and_overparam)



* 2021-NIPS - FINE Samples for Learning with Noisy Labels. [[Paper]](https://openreview.net/forum?id=QZpx42n0BWr)[[Code]](https://github.com/Kthyeon/FINE_official)



* 2021-NeurIPS - Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks. [[Paper]](https://arxiv.org/abs/2103.14749) [[Demo]](https://labelerrors.com/) [[Code]](https://github.com/cleanlab/label-errors) [[Blog Post]](https://l7.curtisnorthcutt.com/label-errors)



* 2021-NeurIPS - Understanding and Improving Early Stopping for Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2106.15853v2)



* 2021-Arxiv - Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation. [[Paper]](https://arxiv.org/abs/2103.00528)



* 2021-Arxiv - A Framework using Contrastive Learning for Classification with Noisy Labels. [[Paper]](https://arxiv.org/abs/2104.09563)



* 2021 - An Instance-Dependent Simulation Framework for Learning with Label Noise. [[Paper]](https://arxiv.org/pdf/2107.11413v4.pdf) [[Project Page]](https://github.com/deepmind/deepmind-research/tree/master/noisy_label)



* 2021-ECML - Estimating the Electrical Power Output of Industrial Devices with End-to-End Time-Series Classification in the Presence of Label Noise. [[Paper]](https://arxiv.org/pdf/2105.00349.pdf) [[Code]](https://github.com/Castel44/SREA)



* 2021-MM - Co-learning: Learning from Noisy Labels with Self-supervision. [[Paper]](https://arxiv.org/abs/2108.04063) [[Code]](https://github.com/chengtan9907/co-training-based_noisy-label-learning)



* 2021-IJCAI - Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion. [[Paper]](https://arxiv.org/abs/2106.09291)



* 2022-WSDM - Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels. [[Paper]](https://arxiv.org/pdf/2201.00232.pdf) [[Code]](https://github.com/enyandai/rsgnn)



* 2022-Arxiv - Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimation. [[Paper]](https://arxiv.org/pdf/2203.10858v1.pdf)



* 2022-AAAI - Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation. [[Paper]](https://arxiv.org/pdf/2103.11594.pdf) [[Code]](https://github.com/YaoruLuo/Deep-Neural-Networks-Learn-Meta-Structures-from-Noisy-Labels-in-Semantic-Segmentation)



* 2022-AAAI - Noise-robust Learning from Multiple Unsupervised Sources of Inferred Labels. [[Paper]](https://ojs.aaai.org/index.php/AAAI/article/view/20806/20565)



* 2022-ICLR - PiCO: Contrastive Label Disambiguation for Partial Label Learning. [[Paper]](https://openreview.net/pdf?id=EhYjZy6e1gJ) [[Code]](https://github.com/hbzju/pico)



* 2022-CVPR - UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning. [[Paper]](https://arxiv.org/pdf/2203.14542v1.pdf) [[Code]](https://github.com/nazmul-karim170/unicon-noisy-label)



* 2022-CVPR - Few-shot Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2204.05494) [[Code]](https://github.com/facebookresearch/noisy_few_shot)



* 2022-CVPR - Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2203.07788) [[Code]](https://github.com/Yikai-Wang/SPR-LNL)



* 2022-CVPR - Large-Scale Pre-training for Person Re-identification with Noisy Labels. [[Paper]](https://arxiv.org/abs/2203.16533) [[Code]](https://github.com/DengpanFu/LUPerson-NL)



* 2022-CVPR - Adaptive Early-Learning Correction for Segmentation from Noisy Annotations. [[Paper]](https://arxiv.org/abs/2110.03740) [[Code]](https://github.com/Kangningthu/ADELE)



* 2022-CVPR - Selective-Supervised Contrastive Learning with Noisy Labels. [[Paper]](https://arxiv.org/abs/2203.04181) [[Code]](https://github.com/ShikunLi/Sel-CL)



* 2022-CVPR - Learning with Neighbor Consistency for Noisy Labels. [[Paper]](https://arxiv.org/abs/2202.02200)



* 2022-CVPR - Learning with Twin Noisy Labels for Visible-Infrared Person Re-Identification. [[Paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_Learning_With_Twin_Noisy_Labels_for_Visible-Infrared_Person_Re-Identification_CVPR_2022_paper.pdf) [[Code]](https://github.com/XLearning-SCU/2022-CVPR-DART)



* 2022-ICML - From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model. [[Paper]](https://proceedings.mlr.press/v162/bae22a/bae22a.pdf) [[Code]](https://github.com/BaeHeeSun/NPC)



* 2022-NIPS - MVP-N: A Dataset and Benchmark for Real-World Multi-View Object Classification. [[Paper]](https://proceedings.neurips.cc/paper_files/paper/2022/file/819b8452be7d6af1351d4c4f9cbdbd9b-Paper-Datasets_and_Benchmarks.pdf) [[Code]](https://github.com/SMNUResearch/MVP-N)



* 2022-BMVC - SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise. [[Paper]](https://arxiv.org/abs/2111.11288) [[Code]](https://github.com/MrChenFeng/SSR_BMVC2022)



* 2023-WACV - Adaptive Sample Selection for Robust Learning under Label Noise. [[Paper]](https://arxiv.org/abs/2106.15292) [[Code]](https://github.com/dbp1994/masters_thesis_codes/tree/main/BARE)



* 2023-WACV - Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels. [[Paper]](https://arxiv.org/abs/2210.08826) [[Code]](https://github.com/btsmart/bootstrapping-label-noise)



## Survey



* 2014-TNLS - Classification in the Presence of Label Noise: a Survey. [[Paper]](https://ieeexplore.ieee.org/document/6685834)



* 2019-KBS - Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey. [[Paper]](https://arxiv.org/abs/1912.05170)



* 2020-SIBGRAPI - A Survey on Deep Learning with Noisy Labels:How to train your model when you cannot trust on the annotations?. [[Paper]](https://arxiv.org/abs/2012.03061) [[Code]](https://github.com/filipe-research/tutorial_noisylabels)



* 2020-MIA - Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. [[Paper]](https://arxiv.org/abs/1912.02911)



* 2020 - Learning from Noisy Labels with Deep Neural Networks: A Survey. [[Paper]](https://arxiv.org/abs/2007.08199) [[Project Page]](https://github.com/songhwanjun/Awesome-Noisy-Labels)



## Github



* [Advances-in-Label-Noise-Learning](https://github.com/weijiaheng/Advances-in-Label-Noise-Learning)

* [Awesome-Noisy-Labels](https://github.com/songhwanjun/Awesome-Noisy-Labels)

* [Search 'Noisy Label' Results](https://github.com/search?p=1&q=noisy+label&type=Repositories&utf8=%E2%9C%93)

* [Noisy Labels with Jupyter  Notebook](https://github.com/udibr/noisy_labels)

* [Noisy Label Neural Network1-Tensorflow](https://github.com/EstherMaria/NoisyLabelNeuralNetwork)

* [Noisy Label Neural Network2-Chainer](https://github.com/Ryo-Ito/Noisy-Labels-Neural-Network)

* [Multi-tasking Learning With Unreliable Labels](https://github.com/debjitpaul/Multi-tasking_Learning_With_Unreliable_Labels)

* [Keras-noisy-lables-finetune](https://github.com/nagash91/keras-noisy-lables-finetune)

* [Light CNN for Deep Face Recognition, in Tensorflow](https://github.com/yxu0611/Tensorflow-implementation-of-LCNN)

* [Rankpruning](https://github.com/cgnorthcutt/rankpruning)

* [Cleanlab: machine learning python package for learning with noisy labels and finding label errors in datasets](https://github.com/cgnorthcutt/cleanlab)

* [Deep Learning with Label Noise](https://github.com/gorkemalgan/deep_learning_with_noisy_labels_literature)

* [Deep Learning for Segmentation When Experts Disagree with Each Other](https://github.com/moucheng2017/Learn_Noisy_Labels_Medical_Images)

* [Fair classification with group label noise](https://github.com/wenshuoguo/robust-fairness-code)



## Others



* [Deep Learning Package-Chainer Tutorial](https://docs.chainer.org/en/stable/tutorial/index.html)

* [Paper-Semi-Supervised Learning Literature Survey](http://pages.cs.wisc.edu/~jerryzhu/pub/ssl_survey.pdf)

* [Cross Validated-Classification with Noisy Labels](https://stats.stackexchange.com/questions/218656/classification-with-noisy-labels)

* [A little talk on label noise](http://knowdive.disi.unitn.it/2018/09/a-little-talk-on-label-noise/)



## Acknowledgements



Some of the above contents are borrowed from [Noisy-Labels-Problem-Collection](https://github.com/GuokaiLiu/Noisy-Labels-Problem-Collection)