mlsanityData to 7 Oct 2026

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

arXiv 2212.03462 ↗First posted 7 Dec 2022cs.CV cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels. Motivated by biological findings that the amplitude spectrum (AS) and phase spectrum (PS) in the frequency domain play different roles in the animal's vision system, we observe that PS, which captures more semantic information, can increase the robustness of DNNs to label noise, more so than AS can. We thus propose early stops at different times for AS and PS by disentangling the features of some layer(s) into AS and PS using Discrete Fourier Transform (DFT) during training. Our proposed Phase-AmplituDe DisentangLed Early Stopping (PADDLES) method is shown to be effective on both synthetic and real-world label-noise datasets. PADDLES outperforms other early stopping methods and obtains state-of-the-art performance.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 50 of its 78 references that are in the map. First posted on arXiv 7 Dec 2022.

Builds on

50 of 78 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  10. 2016Deep Networks with Stochastic Depthcited by 973
  11. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  12. 2017A Closer Look at Memorization in Deep Networkscited by 936
38 more
  1. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  2. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  3. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  4. 2020A Survey on Visual Transformercited by 653
  5. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  6. 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 529
  7. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  8. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  9. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  10. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  11. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  12. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  13. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  14. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  15. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  16. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  17. 2017Decoupling "when to update" from "how to update"cited by 230
  18. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  19. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  20. 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 158
  21. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  22. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  23. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  24. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  25. 2021Deep Learning with Label Differential Privacycited by 113
  26. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  27. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  28. 2017Learning with Biased Complementary Labelscited by 93
  29. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  30. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  31. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  32. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  33. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  34. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  35. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  36. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  37. 2021Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approachcited by 32
  38. 2018Robustness of Conditional GANs to Noisy Labelscited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 1; 2025: 2; 2026: 2.

10 papers.

  1. 2023FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learningcited by 20
  2. 2024Spatial Structure Constraints for Weakly Supervised Semantic Segmentationcited by 17
  3. 2023Fairness Improves Learning from Noisily Labeled Long-Tailed Datacited by 5
  4. 2023Unleashing the Potential of Regularization Strategies in Learning with Noisy Labelscited by 5
  5. 2023Improve Noise Tolerance of Robust Loss via Noise-Awarenesscited by 3
  6. 2025Robust Classification with Noisy Labels Based on Posterior Maximizationcited by 2
  7. 2025Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learningcited by 1
  8. 2023Channel-Wise Contrastive Learning for Learning with Noisy Labelscited by 0
  9. 2026Variational Rectification Inference for Learning with Noisy Labelscited by 0
  10. 2026XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Spacecited by 0