Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Not on the map. Why?
Abstract (arXiv)
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and utilize their semantics, we propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi initially divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Subsequently, the distances between the unconfident samples and the prototype vectors are calculated to facilitate noise classification. Based on these distances, the labels are either corrected or retained, resulting in the refinement of the confident and unconfident datasets. Finally, we introduce a semi-supervised learning method to enhance training. Empirical evaluations on a real-world annotated dataset substantiate the robustness of Proto-semi in handling the problem of learning from noisy labels. Meanwhile, the prototype-based repartitioning strategy is shown to be effective in mitigating the adverse impact of label noise. Our code and data are available at https://github.com/fuxiAIlab/ProtoSemi.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 28 Jul 2023.
Builds on
35 of 45 references.
References · 35
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
- 2017A Closer Look at Memorization in Deep Networkscited by 942
- 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
- 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
- 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
23 more
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
- 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
- 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
- 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
- 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
- 2020Does label smoothing mitigate label noise?cited by 204
- 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
- 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
- 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 127
- 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 113
- 2015Webly Supervised Learning of Convolutional Networkscited by 95
- 2022Robust Training under Label Noise by Over-parameterizationcited by 93
- 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
- 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 88
- 2021FINE Samples for Learning with Noisy Labelscited by 82
- 2020A Topological Filter for Learning with Label Noisecited by 76
- 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
- 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
- 2017Deep Learning from Noisy Image Labels with Quality Embeddingcited by 46
- 2017Learning Deep Networks from Noisy Labels with Dropout Regularizationcited by 32
- 2020EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labelscited by 28
- 2023PASS: Peer-Agreement based Sample Selection for training with Noisy Labelscited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.