Semi-supervised Learning by Disentangling and Self-ensembling over Stochastic Latent Space
The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In this work, we hypothesize – from the generalization perspective – that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space. To this end, we present a stacked SSL model that utilizes unsupervised disentangled representation learning as the stochastic embedding for self-ensembling. We evaluate the presented model for multi-label classification using chest X-ray images, demonstrating its improved performance over related SSL models as well as the interpretability of its disentangled representations.
KeywordsSemi-supervised learning Self-ensembling Disentangled representation learning
This work is supported by NSF CAREER ACI-1350374 and NIH NHLBI R15HL140500.
- 2.Chartsias, A., et al.: Factorised spatial representation learning: application in semi-supervised myocardial segmentation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 490–498. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_55CrossRefGoogle Scholar
- 3.Ghimire, S., Gyawali, P.K., Dhamala, J., Sapp, J.L., Horacek, M., Wang, L.: Improving generalization of deep networks for inverse reconstruction of image sequences. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 153–166. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_12CrossRefGoogle Scholar
- 4.Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI (2019)Google Scholar
- 5.Kawaguchi, K., Bengio, Y., Verma, V., Kaelbling, L.P.: Generalization in machine learning via analytical learning theory. arXiv preprint arXiv:1802.07426 (2018)
- 6.Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: NeurIPS (2014)Google Scholar
- 7.Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2013)Google Scholar
- 8.Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: ICLR (2017)Google Scholar
- 10.Madani, A., Moradi, M., Karargyris, A., Syeda-Mahmood, T.: Semi-supervised learning with generative adversarial networks for chest x-ray classification with ability of data domain adaptation. In: ISBI (2018)Google Scholar
- 11.Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: ICML (2017)Google Scholar