Papers
Topics
Authors
Recent
Search
2000 character limit reached

Potential Energy based Mixture Model for Noisy Label Learning

Published 2 May 2024 in cs.LG and cs.AI | (2405.01186v1)

Abstract: Training deep neural networks (DNNs) from noisy labels is an important and challenging task. However, most existing approaches focus on the corrupted labels and ignore the importance of inherent data structure. To bridge the gap between noisy labels and data, inspired by the concept of potential energy in physics, we propose a novel Potential Energy based Mixture Model (PEMM) for noise-labels learning. We innovate a distance-based classifier with the potential energy regularization on its class centers. Embedding our proposed classifier with existing deep learning backbones, we can have robust networks with better feature representations. They can preserve intrinsic structures from the data, resulting in a superior noisy tolerance. We conducted extensive experiments to analyze the efficiency of our proposed model on several real-world datasets. Quantitative results show that it can achieve state-of-the-art performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Unsupervised label noise modeling and loss correction.
  2. C, J. (2009). Textbook Of Engineering Physics. Prentice-Hall Of India Pvt. Limited.
  3. Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 3296–3303.
  4. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4690–4699.
  5. Fort, S. (2017). Gaussian prototypical networks for few-shot learning on omniglot.
  6. Robust loss functions under label noise for deep neural networks.
  7. Recent advances in large margin learning.
  8. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
  9. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In International Conference on Machine Learning, pages 2304–2313. PMLR.
  10. Kobourov, S. G. (2012). Spring embedders and force directed graph drawing algorithms. Computer Science.
  11. Learning multiple layers of features from tiny images.
  12. Dividemix: Learning with noisy labels as semi-supervised learning.
  13. Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks.
  14. Learning from noisy labels with distillation. In Proceedings of the IEEE International Conference on Computer Vision, pages 1910–1918.
  15. Decoupling "when to update" from "how to update".
  16. McCall, R. (2010). Physics of the Human Body. Johns Hopkins University Press.
  17. Can gradient clipping mitigate label noise? In International Conference on Learning Representations.
  18. Making deep neural networks robust to label noise: A loss correction approach. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1944–1952.
  19. Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596.
  20. Learning from noisy labels with deep neural networks: A survey.
  21. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
  22. Learning from massive noisy labeled data for image classification. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  23. Vahdat, A. (2017). Toward robustness against label noise in training deep discriminative neural networks. arXiv preprint arXiv:1706.00038.
  24. Visualizing data using t-sne. Journal of machine learning research, 9(11).
  25. An overview of statistical learning theory. IEEE Trans Neural Netw, 10(5):988–999.
  26. Cosface: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5265–5274.
  27. Iterative learning with open-set noisy labels. IEEE.
  28. Symmetric cross entropy for robust learning with noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 322–330.
  29. Learning from massive noisy labeled data for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2691–2699.
  30. Searching to exploit memorization effect in learning with noisy labels. In International Conference on Machine Learning, pages 10789–10798. PMLR.
  31. Learning diverse and discriminative representations via the principle of maximal coding rate reduction. Advances in Neural Information Processing Systems, 33.
  32. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412.
  33. Generalized cross entropy loss for training deep neural networks with noisy labels.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.