Mitigating Confirmation Bias in Deep Learning with Noisy Labels through Collaborative Network Training
Keywords:
confirmation bias, noisy labels, collaborative training, deep learningAbstract
Confirmation bias in deep learning arises when models trained on datasets with noisy labels tend to reinforce incorrect predictions, leading to suboptimal learning and reduced generalization performance. This paper proposes a collaborative network training framework to mitigate confirmation bias in the presence of label noise. In the proposed method, two networks are trained simultaneously, each selecting clean samples for the other to learn from. This cross-training strategy prevents individual networks from overfitting to noisy labels and helps preserve model diversity. The framework also incorporates a sample agreement mechanism and consistency regularization to further stabilize training and improve robustness. Experimental evaluations on benchmark datasets including CIFAR-10, CIFAR-100, and Clothing1M show that the proposed approach outperforms existing noise-robust training methods, achieving higher accuracy and better noise tolerance. The results validate the effectiveness of collaborative learning in reducing confirmation bias and improving model reliability under label noise.
References
Ahn, C., Kim, K., Baek, J., Lim, J., and Han, S. 2023. Sample-wise label confidence incorporation for learning with noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1823–1832.
Arazo, E., Ortego, D., Albert, P., O’Connor, N. E., and McGuinness, K. 2019. Unsupervised label noise modeling and loss correction. In Proceedings of the International Conference on Machine Learning (ICML), 312–321.
Arpit, D., Jastrzebski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., Maharaj, T., Fischer, A., Courville, A., Bengio, Y., and Lacoste-Julien, S. 2017. A closer look at memorization in deep networks. In Proceedings of the International Conference on Machine Learning (ICML), 233–242.
Berthelot, D., Carlini, N., Cubuk, E. D., Kurakin, A., Sohn, K., Zhang, H., and Raffel, C. 2019. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv:1911.09785.
Berthelot, D., Carlini, N., Goodfellow, I. J., Papernot, N., Oliver, A., and Raffel, C. 2019. MixMatch: A holistic approach to semi-supervised learning. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 5049–5059.
Chang, W., Shi, Y., and Wang, J. 2023. Csot: Curriculum and structure-aware optimal transport for learning with noisy labels. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36, 8528–8541.
Chen, H., Tao, R., Fan, Y., Wang, Y., Wang, J., Schiele, B., Xie, X., Raj, B., and Savvides, M. 2023. SoftMatch: Addressing the quantity-quality tradeoff in semi-supervised learning. In Proceedings of the 11th International Conference on Learning Representations, 1–21.
Chen, J., Zhang, R., Yu, T., Sharma, R., Xu, Z., Sun, T., and Chen, C. 2023. Label-retrieval-augmented diffusion models for learning from noisy labels. In Proceedings of the Advances in Neural Information Processing Systems. A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36, Curran Associates, Inc., 66499–66517.
Chen, M., Cheng, H., Du, Y., Xu, M., Jiang, W., and Wang, C. 2023. Two wrongs don’t make a right: Combating confirmation bias in learning with label noise. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 14765–14773.
Chen, P., Liao, B. B., Chen, G., and Zhang, S. 2019. Understanding and utilizing KS trained with noisy labels. In Proceedings of the International Conference on Machine Learning. PMLR, 1062–1070.
Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 1597–1607.
Chen, W., Zhu, C., and Li, M. 2023. Sample prior guided robust model learning to suppress noisy labels. In Machine Learning and Knowledge Discovery in Databases: Research Track. Danai Koutra, Claudia Plant, Manuel Gomez Rodriguez, Elena Baralis, and Francesco Bonchi (Eds.). Springer Nature Switzerland, Cham, 3–19.
Cheng, H., Zhu, Z., Li, X., Gong, Y., Sun, X., and Liu, Y. 2020. Learning with instance-dependent label noise: A sample sieve approach. arXiv:2010.02347.
Cheng, H., Zhu, Z., Sun, X., and Liu, Y. 2023. Mitigating memorization of noisy labels via regularization between representations. In Proceedings of the 11th International Conference on Learning Representations, 1–27.
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., and Le, Q. V. 2019. Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 113–123.
Feng, C., Ren, Y., and Xie, X. 2023. Ot-filter: An optimal transport filter for learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16164–16174.
Guo, D., Li, K., Hu, B., Zhang, Y., and Wang, M. 2024. Benchmarking micro-action recognition: Dataset, methods, and applications. IEEE Transactions on Circuits and Systems for Video Technology 34, 7 (2024), 6238–6252.
Guo, Y., Zhang, L., Hu, Y., He, X., and Gao, J. 2016. MS-Celeb-1M: A dataset and benchmark for large-scale face recognition. In Proceedings of the Conference on Computer Vision (ECCV ’16). Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.), Springer International Publishing, Cham, 87–102.
Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I., and Sugiyama, M. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 31, 8536–8546.
He, K., Zhang, X., Ren, S., and Sun, J. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778.
He, K., Zhang, X., Ren, S., and Sun, J. 2016. Identity mappings in deep residual networks. In Proceedings of the 14th European Conference on Computer Vision (ECCV ’16). Springer, 630–645.
Hong, D., Yao, J., Li, C., Meng, D., Yokoya, N., and Chanussot, J. 2023. Decoupled-and-coupled networks: Self-supervised hyperspectral image super-resolution with subpixel fusion. IEEE Transactions on Geoscience and Remote Sensing 61 (2023), 1–12.
Hong, D., Zhang, B., Li, H., Li, Y., Yao, J., Li, C., Werner, M., Chanussot, J., Zipf, A., and Zhu, X. X. 2023. Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks. Remote Sensing of Environment 299 (2023), 113856.
Hong, D., Zhang, B., Li, X., Li, Y., Li, C., Yao, J., Yokoya, N., Li, H., Ghamisi, P., Jia, X., et al. 2024. SpectralGPT: Spectral remote sensing foundation model. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (2024), 5227–5244.
Huang, Z., Zhang, J., and Shan, H. 2023. Twin contrastive learning with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11661–11670.
Iscen, A., Valmadre, J., Arnab, A., and Schmid, C. 2022. Learning with neighbor consistency for noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4672–4681.
Jiang, L., Zhou, Z., Leung, T., Li, L., and Fei-Fei, L. 2018. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings International Conference on Machine Learning (ICML). PMLR, 2304–2313.
Karim, N., Rizve, M. N., Rahnavard, N., Mian, A., and Shah, M. 2022. UniCon: Combating label noise through uniform selection and contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9676–9686.
Kim, J., Baratin, A., Zhang, Y., and Lacoste-Julien, S. 2023. CrossSplit: mitigating label noise memorization through data splitting. In Proceedings of the International Conference on Machine Learning. PMLR, 16377–16392.
Krizhevsky, A. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report.
Le, Y., and Yang, X. 2015. Tiny ImageNet Visual Recognition Challenge. CS 231N 7.
Li, J., Socher, R., and Hoi, S. C. H. 2020. Dividemix: Learning with noisy labels as semi-supervised learning. In Proceedings International Conference on Learning Representations (ICLR), 1–14.
Li, J., Wu, S., Liu, C., Yu, Z., and Wong, H.-S. 2019. Semi-supervised deep coupled ensemble learning with classification landmark exploration. IEEE Transactions on Image Processing 29 (2019), 538–550.
Li, J., Xiong, C., and Hoi, S. C. H. 2021. Learning from noisy data with robust representation learning. In Proceedings IEEE International Conference on Computer Vision (ICCV), 9485–9494.
Li, J., Yuan, J., and Li, Z. 2023. Tp-fer: An effective three-phase noise-tolerant recognizer for facial expression recognition. ACM Transactions on Multimedia Computing, Communications, and Applications 19, 3, Article 113 (Mar. 2023), 17 pages.
Li, S., Deng, W., and Du, J. 2017. Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2852–2861.
Li, S., Xia, X., Ge, S., and Liu, T. 2022. Selective-supervised contrastive learning with noisy labels. arXiv:2203.04181.
Li, W., Wang, L., Li, W., Agustsson, E., and Van Gool, L. 2017. Webvision database: Visual learning and understanding from web data. arXiv:1708.02862.
Li, Y., Han, H., Shan, S., and Chen, X. 2023. DISC: Learning from noisy labels via dynamic instance-specific selection and correction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 24070–24079.
Liu, S., Niles-Weed, J., Razavian, N., and Fernandez-Granda, C. 2020. Early-learning regularization prevents memorization of noisy labels. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 20331–20342.
Liu, Y., and Guo, H. 2020. Peer loss functions: Learning from noisy labels without knowing noise rates. In Proceedings of the International Conference on Machine Learning. PMLR, 6226–6236.
Lu, Y., and He, W. 2022. SELC: Self-ensemble label correction improves learning with noisy labels. arXiv:2205.01156.
Lukov, T., Zhao, N., Lee, G. H., and Lim, S.-N. 2022. Teaching with soft label smoothing for mitigating noisy labels in facial expressions. In Proceedings of the European Conference on Computer Vision. Springer, 648–665.
Malach, E., and Shalev-Shwartz, S. 2017. Decoupling “when to update” from “how to update”. In Proceedings of the Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30, Curran Associates, Inc.
Mohri, M., Rostamizadeh, A., and Talwalkar, A. 2018. Foundations of Machine Learning. MIT press.
Nettleton, D. F., Orriols-Puig, A., and Fornells, A. 2010. A study of the effect of different types of noise on the precision of supervised learning techniques. Artificial Intelligence Review 33 (2010), 275–306.
Pan, H., Cao, Y., Wang, X., and Yang, X. 2023. Finding and editing multi-modal neurons in pre-trained transformer. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 1012–1037.
Patrini, G., Rozza, A., Menon, A. K., Nock, R., and Qu, L. 2017. Making deep neural networks robust to label noise: A loss correction approach. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1944–1952.
Permuter, H., Francos, J., and Jermyn, I. 2006. A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recognition 39, 4 (2006), 695–706.
Sarfraz, F., Arani, E., and Zonooz, B. 2021. Noisy concurrent training for efficient learning under label noise. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 3159–3168.
She, J., Hu, Y., Shi, H., Wang, J., Shen, Q., and Mei, T. 2021. Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6248–6257.
Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C., Cubuk, E. D., Kurakin, A., and Li, C.-L. 2020. FixMatch: Simplifying semi-supervised learning with consistency and confidence. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 596–608.
Song, P., Guo, D., Cheng, J., and Wang, M. 2023. Contextual attention network for emotional video captioning. IEEE Transactions on Multimedia 25 (2023), 1858–1867.
Song, P., Guo, D., Yang, X., Tang, S., and Wang, M. 2024. Emotional video captioning with vision-based emotion interpretation network. IEEE Transactions on Image Processing 33 (2024), 1122–1135.
Song, P., Guo, D., Yang, X., Tang, S., Yang, E., and Wang, M. 2023. Emotion-prior awareness network for emotional video captioning. In Proceedings of the 31st ACM International Conference on Multimedia, 589–600.
Song, P., Zhou, Y., Yang, X., Liu, D., Hu, Z., Wang, D., and Wang, M. 2024. Efficiently gluing pre-trained language and vision models for image captioning. ACM Transactions on Intelligent Systems and Technology 15, 6 (2024), 1–16.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. 2017. Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, 4278–4284.
Tanaka, D., Ikami, D., Yamasaki, T., and Aizawa, K. 2018. Joint optimization framework for learning with noisy labels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5552–5560.
Tarvainen, A., and Valpola, H. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 1195–1204.
Tran, T. Q., Kang, M., and Kim, D. 2021. Rankingmatch: Delving into semi-supervised learning with consistency regularization and ranking loss. arXiv:2110.04430.
Tu, Y., Zhang, B., Li, Y., Liu, L., Li, J., Wang, Y., Wang, C., and Zhao, C. R. 2023. Learning from noisy labels with decoupled meta label purifier. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 19934–19943.
Tu, Y., Zhang, B., Li, Y., Liu, L., Li, J., Zhang, J., Wang, Y., Wang, C., and Zhao, C. R. 2023. Learning with noisy labels via self-supervised adversarial noisy masking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16186–16195.
Wang, K., Peng, X., Yang, J., Lu, S., and Qiao, Y. 2020. Suppressing uncertainties for large-scale facial expression recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6897–6906.
Wei, H., Feng, L., Chen, X., and An, B. 2020. Combating noisy labels by agreement: A joint training method with co-regularization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 13726–13735.
Wei, Q., Feng, L., Sun, H., Wang, R., Guo, C., and Yin, Y. 2023. Fine-grained classification with noisy labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11651–11660.
Wu, H., and Sun, J. 2024. Robust image classification with noisy labels by negative learning and feature space renormalization. IEEE Transactions on Multimedia (2024), 1–12.
Wu, Z., and Cui, J. 2023. LA-Net: Landmark-aware learning for reliable facial expression recognition under label noise. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 20698–20707.
Xia, X., Han, B., Zhan, Y., Yu, J., Gong, M., Gong, C., and Liu, T. 2023. Combating noisy labels with sample selection by mining high-discrepancy examples. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1833–1843.
Xia, X., Liu, T., Han, B., Wang, N., Gong, M., Niu, G., Tao, D., and Sugiyama, M. 2020. Part-dependent label noise: Towards instance-dependent label noise. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 7597–7610.
Xia, X., Liu, T., Wang, N., Han, B., Gong, C., Niu, G., and Sugiyama, M. 2019. Are anchor points really indispensable in label-noise learning? In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 6838–6849.
Xiao, T., Xia, T., Yang, Y., Huang, C., and Wang, X. 2015. Learning from massive noisy labeled data for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2691–2699.
Xu, Y., Cao, P., Kong, Y., and Wang, Y. 2019. L_dmi: A novel information-theoretic loss function for training deep nets robust to label noise. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32, 6225–6236.
Yang, X., Chang, T., Zhang, T., Wang, S., Hong, R., and Wang, M. 2024. Learning hierarchical visual transformation for domain generalizable visual matching and recognition. International Journal of Computer Vision 132 (2024), 1–27.
Yang, X., Dong, J., Cao, Y., Wang, X., Wang, M., and Chua, T.-S. 2020. Tree-augmented cross-modal encoding for complex-query video retrieval. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 1339–1348.
Yang, X., Feng, F., Ji, W., Wang, M., and Chua, T.-S. 2021. Deconfounded video moment retrieval with causal intervention. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1–10.
Yang, X., Wang, S., Dong, J., Dong, J., Wang, M., and Chua, T.-S. 2022. Video moment retrieval with cross-modal neural architecture search. IEEE Transactions on Image Processing 31 (2022), 1204–1216.
Yang, X., Zeng, J., Guo, D., Wang, S., Dong, J., and Wang, M. 2024. Robust video question answering via contrastive cross-modality representation learning. Science China Information Sciences 67, 10 (2024), 1–16.
Yao, J., Hong, D., Wang, H., Liu, H., and Chanussot, J. 2023. UCSL: Toward unsupervised common subspace learning for cross-modal image classification. IEEE Transactions on Geoscience and Remote Sensing 61 (2023), 1–12.
Yu, X., Han, B., Yao, J., Niu, G., Tsang, I. W., and Sugiyama, M. 2019. How does disagreement help generalization against label corruption? In Proceedings of the International Conference on Machine Learning (ICML), 7164–7173.
Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M., and Shinozaki, T. 2021. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 34, 18408–18419.
Zhang, C., Bengio, S., Hardt, M., Recht, B., and Vinyals, O. 2017. Understanding deep learning requires rethinking generalization. In Proceedings of the International Conference on Learning Representations (ICLR), 1–15.
Zhang, H., Cisse, M., Dauphin, Y. N., and Lopez-Paz, D. 2017. mixup: Beyond empirical risk minimization. arXiv:1710.09412.
Zhang, W., Wang, Y., and Qiao, Y. 2019. Metacleaner: Learning to hallucinate clean representations for noisy-labeled visual recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7373–7382.
Zhang, Y., Wang, C., and Deng, W. 2021. Relative uncertainty learning for facial expression recognition. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 34, 17616–17627.
Zhang, Y., Wang, C., Ling, X., and Deng, W. 2022. Learn from all: Erasing attention consistency for noisy label facial expression recognition. In Proceedings of the European Conference on Computer Vision. Springer, 418–434.
Zhang, Z., Chen, W., Fang, C., Li, Z., Chen, L., Lin, L., and Li, G. 2023. RankMatch: Fostering confidence and consistency in learning with noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1644–1654.
Zhang, Z., and Sabuncu, M. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31, 8792–8802.
Zhao, G., Li, G., Qin, Y., Liu, F., and Yu, Y. 2022. Centrality and consistency: Two-stage clean samples identification for learning with instance-dependent noisy labels. In Proceedings of the Conference on Computer Vision (ECCV ’22). Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer Nature Switzerland, Cham, 21–37.
Zheng, G., Awadallah, A. H., and Dumais, S. 2021. Meta label correction for noisy label learning. In Proceedings of the Conference on Association for the Advancement of Artificial Intelligence (AAAI), 11053–11061.
Zhou, X., Liu, X., Wang, C., Zhai, D., Jiang, J., and Ji, X. 2021. Learning with noisy labels via sparse regularization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 72–81.
Zhou, Y., Li, X., Liu, F., Wei, Q., Chen, X., Yu, L., Xie, C., Lungren, M. P., and Xing, L. 2024. L2B: Learning to bootstrap robust models for combating label noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 23523–23533.
Zhu, Z., Liu, T., and Liu, Y. 2021. A second-order approach to learning with instance-dependent label noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10113–10123.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Jianhong Wei, Aaliyah M. Farouk
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain full copyright of their published work. By submitting to an ERDAST journal and upon acceptance of the article, the author(s) agree to grant the journal a non-exclusive license to publish, reproduce, distribute, and archive the article. All articles are published under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Under this license: Others may copy, distribute, display, remix, adapt, and build upon the work, even commercially, As long as proper credit is given to the original author(s) and source, A link to the license is provided, an, Any changes are clearly indicated.
???? License link: https://creativecommons.org/licenses/by/4.0/
