Friends and Foes in Learning from Noisy Labels
Not on the map. Why?
Abstract (arXiv)
Learning from examples with noisy labels has attracted increasing attention recently. But, this paper will show that the commonly used CIFAR-based datasets and the accuracy evaluation metric used in the literature are both inappropriate in this context. An alternative valid evaluation metric and new datasets are proposed in this paper to promote proper research and evaluation in this area. Then, friends and foes are identified from existing methods as technical components that are either beneficial or detrimental to deep learning from noisy labeled examples, respectively, and this paper improves and combines technical components from the friends category, including self-supervised learning, new warmup strategy, instance filtering and label correction. The resulting F&F method significantly outperforms existing methods on the proposed nCIFAR datasets and the real-world Clothing1M dataset.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 28 Mar 2021.
Builds on
28 of 37 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
- 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
- 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
- 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
- 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
16 more
- 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
- 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
- 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
- 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 259
- 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
- 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
- 2017Learning from Noisy Labels with Distillationcited by 160
- 2019Meta Label Correction for Noisy Label Learningcited by 108
- 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
- 2017Toward Robustness against Label Noise in Training Deep Discriminative Neural Networkscited by 78
- 2020A Topological Filter for Learning with Label Noisecited by 76
- 2016Factors in Finetuning Deep Model for object detectioncited by 53
- 2020EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labelscited by 28
- 2020NoiseRank: Unsupervised Label Noise Reduction with Dependence Modelscited by 20
- 2015Auxiliary Image Regularization for Deep CNNs with Noisy Labelscited by 14
- 2019A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labelscited by 10
Built on by
Citing papers per year: 2022: 1.
1 paper.