FGCM: Noisy Label Learning via Fine-Grained Confidence Modeling
Source abstract
Abstract
A small portion of mislabeled data can easily limit the performance of deep neural networks (DNNs) due to their high capacity for memorizing random labels. Thus, robust learning from noisy labels has become a key challenge for deep learning due to inadequate datasets with high-quality annotations. Most existing methods involve training models on clean sets by dividing clean samples from noisy ones, resulting in large amounts of mislabeled data being unused. To address this problem, we propose categorizing training samples into five fine-grained clusters based on the difficulty experienced by DNN models when learning them and label correctness. A novel fine-grained confidence modeling (FGCM) framework is proposed to cluster samples into these five categories; with each cluster, FGCM decides whether to accept the cluster data as they are, accept them with label correction, or accept them as unlabeled data. By applying different strategies to the fine-grained clusters, FGCM can better exploit training data than previous methods. Extensive experiments on widely used benchmarks CIFAR-10, CIFAR-100, clothing1M, and WebVision with different ratios and types of label noise demonstrate the superiority of our FGCM.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and Data Classification · Machine Learning and Algorithms · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310007, China
Zhejiang Provincial Key Laboratory for Network Multimedia Technologies, Hangzhou 310007, China
Zhejiang University Embedded System Engineering Research Center, Ministry of Education of China, Hangzhou 310007, China
Funding
National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities
References (47)
Show source-provided references
1. Arpit, D., Jastrzebski, S., Ballas, N., Krueger, D., Bengio, E., and Kanwal, M.S. (2017, January 7–9). A closer look at memorization in deep networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia.
2. Toneva, M., Sordoni, A., des Combes, R.T., Trischler, A., Bengio, Y., and Gordon, G. (2019, January 6–9). An empirical study of example forgetting during deep neural network learning. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
3. Zhang, C., Recht, B., Bengio, S., Hardt, M., and Vinyals, O. (2017, January 24–26). Understanding deep learning requires rethinking generalization. Proceedings of the International Conference on Learning Representations, Toulon, France.
4. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
5. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 26–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
6. Tanaka, D., Ikami, D., Yamasaki, T., and Aizawa, K. (2018, January 18–22). Joint optimization framework for learning with noisy labels. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00582 ↗
7. Classification with Noisy Labels by Importance Reweighting10.1109/TPAMI.2015.2456899 ↗
8. Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., and McGuinness, K. (2019, January 9–15). Unsupervised label noise modeling and loss correction. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
9. Zhang, Z., Zhang, H., Arik, S.O., Lee, H., and Pfister, T. (2020, January 14–19). Distilling effective supervision from severe label noise. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR42600.2020.00931 ↗
10. Robust Semi-Supervised Classification for Noisy Labels Based on Self-Paced Learning
11. Deep Learning from Noisy Image Labels with Quality Embedding
12. Li, S., Xia, X., Ge, S., and Liu, T. (2022, January 21–24). Selective-Supervised Contrastive Learning with Noisy Labels. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00041 ↗
13. TC-Net: Detecting Noisy Labels via Transform Consistency10.1109/TMM.2021.3115635 ↗
14. Bernhardt, M., Castro, D.C., Tanno, R., Schwaighofer, A., Tezcan, K.C., Monteiro, M., Bannur, S., Lungren, M.P., Nori, A., and Glocker, B. (2022). Active label cleaning for improved dataset quality under resource constraints. Nat. Commun., 13.10.1038/s41467-022-28818-3 ↗
15. Liu, S., Niles-Weed, J., Razavian, N., and Fernandez-Granda, C. (2020, January 6–12). Early-learning regularization prevents memorization of noisy labels. Proceedings of the Conference on Neural Information Processing Systems, Virtual.
16. Jiang, L., Zhou, Z., Leung, T., Li, L., and Li, F.-F. (2018, January 10–15). MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.
17. Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., and Hu, W. (2018, January 2–8). Co-teaching: Robust training of deep neural networks with extremely noisy labels. Proceedings of the Conference on Neural Information Processing Systems, Montreal, QC, Canada.
18. Yu, X., Han, B., Yao, J., Niu, G., Tsang, I.W., and Sugiyama, M. (2019, January 9–15). How does disagreement help generalization against label corruption?. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
19. Li, J., Socher, R., and Hoi, S. (2020, January 26–30). Dividemix: Learning with noisy labels as semi-supervised learning. Proceedings of the International Conference on Learning Representations, Virtual.
20. Patrini, G., Rozza, A., Menon, A.K., Nock, R., and Qu, L. (2017, January 22–25). Making deep neural networks robust to label noise: A loss correction approach. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.240 ↗
21. Chen, X., and Gupta, A. (2015, January 13–16). Webly supervised learning of convolutional networks. Proceedings of the International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.168 ↗
22. Xiao, T., Xia, T., Yang, Y., Huang, C., and Wang, X. (2015, January 8–10). Learning from massive noisy labeled data for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
23. Ghosh, A., Kumar, H., and Sastry, P. (2017, January 4–9). Robust loss functions under label noise for deep neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10894 ↗
24. Zhang, Z., and Sabuncu, M. (2018, January 2–8). Generalized cross entropy loss for training deep neural networks with noisy labels. Proceedings of the Conference on Neural Information Processing Systems, Montreal, QC, Canada.
25. Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., and Bailey, J. (2019, January 27–31). Symmetric cross entropy for robust learning with noisy labels. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.10.1109/ICCV.2019.00041 ↗
26. Chen, P., Liao, B.B., Chen, G., and Zhang, S. (2019, January 9–15). Understanding and utilizing deep neural networks trained with noisy labels. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
27. Nguyen, D.T., Mummadi, C.K., Ngo, T.P.N., Nguyen, T.H.P., Beggel, L., and Brox, T. (2020, January 26–30). SELF: Learning to filter noisy labels with self-ensembling. Proceedings of the International Conference on Learning Representations, Virtual.
28. Ortego, D., Arazo, E., Albert, P., and O’Connor, N.E. (2021, January 20–25). Multi-objective interpolation training for robustness to label noise. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Virtual.10.1109/CVPR46437.2021.00654 ↗
29. A study of gaussian mixture models of color and texture features for image classification and segmentation10.1016/j.patcog.2005.10.028 ↗
30. Maximum likelihood from incomplete data via the EM algorithm10.1111/j.2517-6161.1977.tb01600.x ↗
31. Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., and Raffel, C. (2020, January 6–12). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Proceedings of the Conference on Neural Information Processing Systems, Virtual.
32. Krizhevsky, A., Nair, V., and Hinton, G. (2021). CIFAR-10 CIFAR-100, Canadian Institute for Advanced Research.
33. Li, W., Wang, L., Li, W., Agustsson, E., and Gool, L.V. (2017). Webvision database: Visual learning and understanding from web data. arXiv.
34. Song, H., Kim, M., Park, D., and Lee, J. (2019, January 9–15). Prestopping: How does early stopping help generalization against label noise?. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
35. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 8–16). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_38 ↗
36. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 26–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
37. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017, January 4–9). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11231 ↗
38. Yi, K., and Wu, J. (2019, January 16–20). Probabilistic end-to-end noise correction for learning with noisy labels. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00718 ↗
39. Kim, T., Ko, J., Choi, J., and Yun, S.Y. (2021, January 7–10). Fine samples for learning with noisy labels. Proceedings of the Conference on Neural Information Processing Systems, Virtual.
40. Li, J., Wong, Y., Zhao, Q., and Kankanhalli, M.S. (2019, January 16–20). Learning to learn from noisy labeled data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00519 ↗
41. Wu, Y., Shu, J., Xie, Q., Zhao, Q., and Meng, D. (2021, January 2–9). Learn To Purify Noisy Labels via Meta Soft Label Corrector. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.10.1609/aaai.v35i12.17244 ↗
42. Zhang, W., Wang, Y., and Qiao, Y. (2019, January 16–20). Metacleaner: Learning to hallucinate clean representations for noisy-labeled visual recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00755 ↗
43. Malach, E., and Shalev-Shwartz, S. (2017, January 4–7). Decoupling “when to update” from “how to update”. Proceedings of the Conference on Neural Information Processing Systems, Long Beach, CA, USA.
44. Ma, X., Wang, Y., Houle, M., Zhou, S., Erfani, S., Xia, S., Wijewickrema, S., and Bailey, J. (2018, January 10–15). Dimensionality-driven learning with noisy labels. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.10.1109/CVPR.2018.00906 ↗
45. Li, J., Xiong, C., and Hoi, S. (2021, January 11–17). Learning from noisy data with robust representation learning. Proceedings of the International Conference on Computer Vision, Virtual.10.1109/ICCV48922.2021.00935 ↗
46. Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., and Peng, X. (2022, January 21–24). Learning with Twin Noisy Labels for Visible-Infrared Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01391 ↗
47. Wang, Y., Baldwin, T., and Verspoor, K. (2022, January 10–12). Noisy Label Regularisation for Textual Regression. Proceedings of the International Conference on Computational Linguistics, Gyeongju, Korea.10.1162/tacl_a_00483 ↗