Abstract
Consistency regularization has shown superiority in deep semi-supervised learning, which commonly estimates pseudo-label conditioned on each single sample and its perturbations. However, such a strategy ignores the relation between data points, and probably arises error accumulation problems once one sample and its perturbations are integrally misclassified. Against this issue, we propose Neighbor Matching, a pseudo-label estimator that propagates labels for unlabeled samples according to their neighboring ones (labeled samples with the same semantic category) during training in an online manner. Different from existing methods, for an unlabeled sample, our Neighbor Matching defines a mapping function that predicts its pseudo-label conditioned on itself and its local manifold. Concretely, the local manifold is constructed by a memory padding module that memorizes the embeddings and labels of labeled data across different mini-batches. We experiment with two distinct benchmark datasets for semi-supervised classification of thoracic disease and skin lesion, and the results demonstrate the superiority of our approach beyond other state-of-the-art methods. Source code is publicly available at https://github.com/renzhenwang/neighbor-matching.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bachman, P., Alsharif, O., Precup, D.: Learning with pseudo-ensembles. In: Advances in Neural Information Processing Systems, pp. 3365–3373 (2014)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (2015)
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems. pp. 5049–5059 (2019)
Bortsova, G., Dubost, F., Hogeweg, L., Katramados, I., de Bruijne, M.: Semi-supervised medical image segmentation via learning consistency under transformations. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 810–818. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_90
Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)
Cui, W., et al.: Semi-supervised brain lesion segmentation with an adapted mean teacher model. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 554–565. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_43
Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. Adv. Neural Inf. Process. Syst. 17, 529–536 (2004)
Gyawali, P.K., Ghimire, S., Bajracharya, P., Li, Z., Wang, L.: Semi-supervised medical image classification with global latent mixing. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 604–613. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_59
Gyawali, P.K., Li, Z., Ghimire, S., Wang, L.: Semi-supervised learning by disentangling and self-ensembling over stochastic latent space. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 766–774. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_85
Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590–597 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: International Conference on Learning Representations (2017)
Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
Miyato, T., Maeda, S.I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1979–1993 (2018)
Paszke, A., Gross, S., Chintala, S., et al.: Automatic differentiation in PyTorch. In: Advances in Neural Information Processing Systems Workshop Autodiff, pp. 1–4 (2017)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)
Su, H., Shi, X., Cai, J., Yang, L.: Local and global consistency regularized mean teacher for semi-supervised nuclei classification. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 559–567. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_62
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, pp. 1195–1204 (2017)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438–6447. PMLR (2019)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, pp. 3630–3638 (2016)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)
Acknowledgments
This research was supported by National Key R&D Program of China (2020YFA0713900), the Macao Science and Technology Development Fund under Grant 061/2020/A2, the China NSFC projects (62076196, 11690011, 61721002, U1811461).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, R., Wu, Y., Chen, H., Wang, L., Meng, D. (2021). Neighbor Matching for Semi-supervised Learning. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12902. Springer, Cham. https://doi.org/10.1007/978-3-030-87196-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-87196-3_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87195-6
Online ISBN: 978-3-030-87196-3
eBook Packages: Computer ScienceComputer Science (R0)
