Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning (2402.17589v2)

Published 27 Feb 2024 in cs.CV

Abstract: Recently, the usage of Contrastive Representation Learning (CRL) as a pre-training technique improves the performance of learning with noisy labels (LNL) methods. However, instead of pre-training, when trivially combining CRL loss with LNL methods as an end-to-end framework, the empirical experiments show severe degeneration of the performance. We verify through experiments that this issue is caused by optimization conflicts of losses and propose an end-to-end \textbf{PLReMix} framework by introducing a Pseudo-Label Relaxed (PLR) contrastive loss. This PLR loss constructs a reliable negative set of each sample by filtering out its inappropriate negative pairs, alleviating the loss conflicts by trivially combining these losses. The proposed PLR loss is pluggable and we have integrated it into other LNL methods, observing their improved performance. Furthermore, a two-dimensional Gaussian Mixture Model is adopted to distinguish clean and noisy samples by leveraging semantic information and model outputs simultaneously. Experiments on multiple benchmark datasets demonstrate the effectiveness of the proposed method. Code is available at \url{https://github.com/lxysl/PLReMix}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Unsupervised label noise modeling and loss correction. In International Conference on Machine Learning, pages 312–321. PMLR, 2019.
  2. A closer look at memorization in deep networks. In International Conference on Machine Learning, pages 233–242. PMLR, 2017.
  3. Understanding and improving early stopping for learning with noisy labels. Advances in Neural Information Processing Systems, 34:24392–24403, 2021.
  4. Mixmatch: A holistic approach to semi-supervised learning. Advances in Neural Information Processing Systems, 32, 2019.
  5. Unsupervised learning of visual features by contrasting cluster assignments. Advances in Neural Information Processing Systems, 33:9912–9924, 2020.
  6. Social-network analysis using topic models. In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pages 565–574, 2012.
  7. Simpler, faster, stronger: Breaking the log-k curse on contrastive learners with flatnce. arXiv preprint arXiv:2107.01152, 2021.
  8. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning, pages 1597–1607. PMLR, 2020.
  9. Webly supervised learning of convolutional networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1431–1439, 2015.
  10. Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 113–123, 2019.
  11. Multi-label image recognition in anime illustration with graph convolutional networks. In Proceedings of the AAAI Conference on Artificial Intelligence, 2020.
  12. Contrastive learning improves model robustness under label noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2703–2708, 2021.
  13. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in Neural Information Processing Systems, 31, 2018.
  14. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016a.
  15. Identity mappings in deep residual networks. In Proceedings of the European Conference on Computer Vision, pages 630–645. Springer, 2016b.
  16. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9729–9738, 2020.
  17. Self-adaptive training: beyond empirical risk minimization. Advances in Neural Information Processing Systems, 33:19365–19376, 2020.
  18. Twin contrastive learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11661–11670, 2023.
  19. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In International Conference on Machine Learning, pages 2304–2313. PMLR, 2018.
  20. Unicon: Combating label noise through uniform selection and contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9676–9686, 2022.
  21. Supervised contrastive learning. Advances in Neural Information Processing Systems, 33:18661–18673, 2020.
  22. Nlnl: Negative learning for noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 101–110, 2019.
  23. The unreasonable effectiveness of noisy data for fine-grained recognition. In Proceedings of the European Conference on Computer Vision, pages 301–320. Springer, 2016.
  24. Learning multiple layers of features from tiny images. 2009.
  25. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90, 2017.
  26. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. International Journal of Computer Vision, 128(7):1956–1981, 2020.
  27. Tiny imagenet visual recognition challenge. CS 231N, 7(7):3, 2015.
  28. Dividemix: Learning with noisy labels as semi-supervised learning. In International Conference on Learning Representations, 2019.
  29. Mopro: Webly supervised learning with momentum prototypes. In International Conference on Learning Representations, 2020a.
  30. Learning from noisy data with robust representation learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9485–9494, 2021.
  31. Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In International conference on artificial intelligence and statistics, pages 4313–4324. PMLR, 2020b.
  32. Selective-supervised contrastive learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 316–325, 2022.
  33. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862, 2017.
  34. Early-learning regularization prevents memorization of noisy labels. Advances in Neural Information Processing Systems, 33:20331–20342, 2020.
  35. Noise resistant graph ranking for improved web image search. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 849–856, 2011.
  36. Exploring the limits of weakly supervised pretraining. In Proceedings of the European Conference on Computer Vision, pages 181–196, 2018.
  37. Augmentation strategies for learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8022–8031, 2021.
  38. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
  39. Multi-objective interpolation training for robustness to label noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6606–6615, 2021.
  40. Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596, 2014.
  41. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 2015.
  42. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
  43. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115(3):211–252, 2015.
  44. Scanmix: Learning from severe label noise via semantic clustering and semi-supervised learning. Pattern Recognition, 134:109121, 2023.
  45. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems, 33:596–608, 2020.
  46. How does early stopping help generalization against label noise? arXiv preprint arXiv:1911.08059, 2019.
  47. Training convolutional networks with noisy labels. In International Conference on Learning Representations, 2015.
  48. Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 2017.
  49. Joint optimization framework for learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5552–5560, 2018.
  50. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  51. Promix: Combating label noise via maximizing clean sample utility. arXiv preprint arXiv:2207.10276, 2022.
  52. Combating noisy labels by agreement: A joint training method with co-regularization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13726–13735, 2020.
  53. Unsupervised feature learning via non-parametric instance discrimination. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3733–3742, 2018.
  54. Learning from massive noisy labeled data for image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2691–2699, 2015.
  55. Noise is also useful: Negative correlation-steered latent contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 31–40, 2022.
  56. Probabilistic end-to-end noise correction for learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7017–7025, 2019.
  57. Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems, 33:5824–5836, 2020.
  58. How does disagreement help generalization against label corruption? In International Conference on Machine Learning, pages 7164–7173. PMLR, 2019.
  59. Understanding deep learning (still) requires rethinking generalization. Communications of the ACM, 64(3):107–115, 2021.
  60. Decoupling representation and classifier for noisy label learning. arXiv preprint arXiv:2011.08145, 2020.
  61. mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, 2018.
  62. Contrast to divide: Self-supervised pre-training for learning with noisy labels. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1657–1667, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Xiaoyu Liu (139 papers)
  2. Beitong Zhou (5 papers)
  3. Cheng Cheng (188 papers)
  4. Zuogong Yue (8 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now